Daily Papers

Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their resource-intensive nature, leading to increased memory footprint, computation complexity, and power consumption. To democratize this high-performance technology and make it more environmentally friendly, it is essential to compress ViT models, reducing their resource requirements while maintaining high performance. In this paper, we introduce a new block-structured pruning to address the resource-intensive issue for ViTs, offering a balanced trade-off between accuracy and hardware acceleration. Unlike unstructured pruning or channel-wise structured pruning, block pruning leverages the block-wise structure of linear layers, resulting in more efficient matrix multiplications. To optimize this pruning scheme, our paper proposes a novel hardware-aware learning objective that simultaneously maximizes speedup and minimizes power consumption during inference, tailored to the block sparsity structure. This objective eliminates the need for empirical look-up tables and focuses solely on reducing parametrized layer connections. Moreover, our paper provides a lightweight algorithm to achieve post-training pruning for ViTs, utilizing second-order Taylor approximation and empirical optimization to solve the proposed hardware-aware objective. Extensive experiments on ImageNet are conducted across various ViT architectures, including DeiT-B and DeiT-S, demonstrating competitive performance with other pruning methods and achieving a remarkable balance between accuracy preservation and power savings. Especially, we achieve up to 3.93x and 1.79x speedups on dedicated hardware and GPUs respectively for DeiT-B, and also observe an inference power reduction by 1.4x on real-world GPUs.

Parameter-shared pre-trained language models (PLMs) have emerged as a successful approach in resource-constrained environments, enabling substantial reductions in model storage and memory costs without significant performance compromise. However, it is important to note that parameter sharing does not alleviate computational burdens associated with inference, thus impeding its practicality in situations characterized by limited stringent latency requirements or computational resources. Building upon neural ordinary differential equations (ODEs), we introduce a straightforward technique to enhance the inference efficiency of parameter-shared PLMs. Additionally, we propose a simple pre-training technique that leads to fully or partially shared models capable of achieving even greater inference acceleration. The experimental results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs, providing novel insights into more efficient utilization of parameter-shared models in resource-constrained settings.

As the training of giant dense models hits the boundary on the availability and capability of the hardware resources today, Mixture-of-Experts (MoE) models become one of the most promising model architectures due to their significant training cost reduction compared to a quality-equivalent dense model. Its training cost saving is demonstrated from encoder-decoder models (prior works) to a 5x saving for auto-aggressive language models (this work along with parallel explorations). However, due to the much larger model size and unique architecture, how to provide fast MoE model inference remains challenging and unsolved, limiting its practical usage. To tackle this, we present DeepSpeed-MoE, an end-to-end MoE training and inference solution as part of the DeepSpeed library, including novel MoE architecture designs and model compression techniques that reduce MoE model size by up to 3.7x, and a highly optimized inference system that provides 7.3x better latency and cost compared to existing MoE inference solutions. DeepSpeed-MoE offers an unprecedented scale and efficiency to serve massive MoE models with up to 4.5x faster and 9x cheaper inference compared to quality-equivalent dense models. We hope our innovations and systems help open a promising path to new directions in the large model landscape, a shift from dense to sparse MoE models, where training and deploying higher-quality models with fewer resources becomes more widely possible.

While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention mechanisms, resulting in significant inference latency. Through detailed analysis of attention maps in Video Diffusion Transformer (vDiT), we identify three recurring sparsity patterns: diagonal, multi-diagonal, and vertical-stripe structures. And even 3-6\% attention heads can be skipped. Crucially, these patterns exhibit strong layer-depth and head-position correlations but show limited dependence on the input content. Leveraging these findings, we propose Sparse-vDiT, a sparsity acceleration framework for vDiT comprising: 1) Pattern-optimized sparse kernels that replace dense attention with computationally efficient implementations for each identified sparsity pattern. 2) An offline sparse diffusion search algorithm that selects the optimal sparse computation strategy per layer and head via hardware-aware cost modeling. After determining the optimal configuration, we fuse heads within the same layer that share the same attention strategy, enhancing inference efficiency. Integrated into state-of-the-art vDiT models (CogVideoX1.5, HunyuanVideo, and Wan2.1), Sparse-vDiT achieves 2.09times, 2.38times, and 1.67times theoretical FLOP reduction, and actual inference speedups of 1.76times, 1.85times, and 1.58times, respectively, while maintaining high visual fidelity, with PSNR values reaching 24.13, 27.09, and 22.59. Our work demonstrates that latent structural sparsity in vDiTs can be systematically exploited for long video synthesis.

Reinforcement learning agents based on Transformer architectures have achieved impressive performance on sequential decision-making tasks, but their reliance on dense matrix operations makes them ill-suited for energy-constrained, edge-oriented platforms. Spiking neural networks promise ultra-low-power, event-driven inference, yet no prior work has seamlessly merged spiking dynamics with return-conditioned sequence modeling. We present the Spiking Decision Transformer (SNN-DT), which embeds Leaky Integrate-and-Fire neurons into each self-attention block, trains end-to-end via surrogate gradients, and incorporates biologically inspired three-factor plasticity, phase-shifted spike-based positional encodings, and a lightweight dendritic routing module. Our implementation matches or exceeds standard Decision Transformer performance on classic control benchmarks (CartPole-v1, MountainCar-v0, Acrobot-v1, Pendulum-v1) while emitting fewer than ten spikes per decision, an energy proxy suggesting over four orders-of-magnitude reduction in per inference energy. By marrying sequence modeling with neuromorphic efficiency, SNN-DT opens a pathway toward real-time, low-power control on embedded and wearable devices.

The optimal training configurations of large language models (LLMs) with respect to model sizes and compute budgets have been extensively studied. But how to optimally configure LLMs during inference has not been explored in sufficient depth. We study compute-optimal inference: designing models and inference strategies that optimally trade off additional inference-time compute for improved performance. As a first step towards understanding and designing compute-optimal inference methods, we assessed the effectiveness and computational efficiency of multiple inference strategies such as Greedy Search, Majority Voting, Best-of-N, Weighted Voting, and their variants on two different Tree Search algorithms, involving different model sizes and computational budgets. We found that a smaller language model with a novel tree search algorithm typically achieves a Pareto-optimal trade-off. These results highlight the potential benefits of deploying smaller models equipped with more sophisticated decoding algorithms in budget-constrained scenarios, e.g., on end-devices, to enhance problem-solving accuracy. For instance, we show that the Llemma-7B model can achieve competitive accuracy to a Llemma-34B model on MATH500 while using 2times less FLOPs. Our findings could potentially apply to any generation task with a well-defined measure of success.

Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of these models. Previous efforts, including techniques like model pruning, quantization, and hardware optimization, have made significant strides in this direction. However, there remains a need for more effective on device AI solutions that balance energy efficiency with model performance. In this paper, we propose a novel approach to reduce the energy requirements of inference of CNNs. Our methodology employs two small Complementary CNNs that collaborate with each other by covering each other's "weaknesses" in predictions. If the confidence for a prediction of the first CNN is considered low, the second CNN is invoked with the aim of producing a higher confidence prediction. This dual-CNN setup significantly reduces energy consumption compared to using a single large deep CNN. Additionally, we propose a memory component that retains previous classifications for identical inputs, bypassing the need to re-invoke the CNNs for the same input, further saving energy. Our experiments on a Jetson Nano computer demonstrate an energy reduction of up to 85.8% achieved on modified datasets where each sample was duplicated once. These findings indicate that leveraging a complementary CNN pair along with a memory component effectively reduces inference energy while maintaining high accuracy.

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions to handle the computational demands. In this paper, we explore the utilization of CPUs for accelerating the inference of large language models. Specifically, we introduce a parallelized approach to enhance throughput by 1) Exploiting the parallel processing capabilities of modern CPU architectures, 2) Batching the inference request. Our evaluation shows the accelerated inference engine gives an 18-22x improvement in the generated token per sec. The improvement is more with longer sequence and larger models. In addition to this, we can also run multiple workers in the same machine with NUMA node isolation to further improvement in tokens/s. Table 2, we have received 4x additional improvement with 4 workers. This would also make Gen-AI based products and companies environment friendly, our estimates shows that CPU usage for Inference could reduce the power consumption of LLMs by 48.9% while providing production ready throughput and latency.

Reducing inference time and energy usage while maintaining prediction accuracy has become a significant concern for deep neural networks (DNN) inference on resource-constrained edge devices. To address this problem, we propose a novel approach based on "converting" autoencoder and lightweight DNNs. This improves upon recent work such as early-exiting framework and DNN partitioning. Early-exiting frameworks spend different amounts of computation power for different input data depending upon their complexity. However, they can be inefficient in real-world scenarios that deal with many hard image samples. On the other hand, DNN partitioning algorithms that utilize the computation power of both the cloud and edge devices can be affected by network delays and intermittent connections between the cloud and the edge. We present CBNet, a low-latency and energy-efficient DNN inference framework tailored for edge devices. It utilizes a "converting" autoencoder to efficiently transform hard images into easy ones, which are subsequently processed by a lightweight DNN for inference. To the best of our knowledge, such autoencoder has not been proposed earlier. Our experimental results using three popular image-classification datasets on a Raspberry Pi 4, a Google Cloud instance, and an instance with Nvidia Tesla K80 GPU show that CBNet achieves up to 4.8x speedup in inference latency and 79% reduction in energy usage compared to competing techniques while maintaining similar or higher accuracy.

This paper introduces PowerInfer-2, a framework designed for high-speed inference of Large Language Models (LLMs) on smartphones, particularly effective for models whose sizes exceed the device's memory capacity. The key insight of PowerInfer-2 is to utilize the heterogeneous computation, memory, and I/O resources in smartphones by decomposing traditional matrix computations into fine-grained neuron cluster computations. Specifically, PowerInfer-2 features a polymorphic neuron engine that adapts computational strategies for various stages of LLM inference. Additionally, it introduces segmented neuron caching and fine-grained neuron-cluster-level pipelining, which effectively minimize and conceal the overhead caused by I/O operations. The implementation and evaluation of PowerInfer-2 demonstrate its capability to support a wide array of LLM models on two smartphones, achieving up to a 29.2x speed increase compared with state-of-the-art frameworks. Notably, PowerInfer-2 is the first system to serve the TurboSparse-Mixtral-47B model with a generation rate of 11.68 tokens per second on a smartphone. For models that fit entirely within the memory, PowerInfer-2 can achieve approximately a 40% reduction in memory usage while maintaining inference speeds comparable to llama.cpp and MLC-LLM. For more details, including a demonstration video, please visit the project site at www.powerinfer.ai/v2.

Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks. However, their real-world deployment is often constrained by high latency during inference due to substantial compute required to process the large number of input tokens (predominantly from the image) by the LLM. To reduce inference costs, one can either downsize the LLM or reduce the number of input image-tokens, the latter of which has been the focus of many recent works around token compression. However, it is unclear what the optimal trade-off is, as both the factors directly affect the VLM performance. We first characterize this optimal trade-off between the number of visual tokens and LLM parameters by establishing scaling laws that capture variations in performance with these two factors. Our results reveal a surprising trend: for visual reasoning tasks, the inference-optimal behavior in VLMs, i.e., minimum downstream error at any given fixed inference compute, is achieved when using the largest LLM that fits within the inference budget while minimizing visual token count - often to a single token. While the token reduction literature has mainly focused on maintaining base model performance by modestly reducing the token count (e.g., 5-10times), our results indicate that the compute-optimal inference regime requires operating under even higher token compression ratios. Based on these insights, we take some initial steps towards building approaches tailored for high token compression settings. Code is available at https://github.com/locuslab/llava-token-compression.

As neural networks grow in size and complexity, inference speeds decline. To combat this, one of the most effective compression techniques -- channel pruning -- removes channels from weights. However, for multi-branch segments of a model, channel removal can introduce inference-time memory copies. In turn, these copies increase inference latency -- so much so that the pruned model can be slower than the unpruned model. As a workaround, pruners conventionally constrain certain channels to be pruned together. This fully eliminates memory copies but, as we show, significantly impairs accuracy. We now have a dilemma: Remove constraints but increase latency, or add constraints and impair accuracy. In response, our insight is to reorder channels at export time, (1) reducing latency by reducing memory copies and (2) improving accuracy by removing constraints. Using this insight, we design a generic algorithm UPSCALE to prune models with any pruning pattern. By removing constraints from existing pruners, we improve ImageNet accuracy for post-training pruned models by 2.1 points on average -- benefiting DenseNet (+16.9), EfficientNetV2 (+7.9), and ResNet (+6.2). Furthermore, by reordering channels, UPSCALE improves inference speeds by up to 2x over a baseline export.

Large language models (LLMs) are widely applied in chatbots, code generators, and search engines. Workloads such as chain-of-thought, complex reasoning, and agent services significantly increase the inference cost by invoking the model repeatedly. Optimization methods such as parallelism, compression, and caching have been adopted to reduce costs, but the diverse service requirements make it hard to select the right method. Recently, specialized LLM inference engines have emerged as a key component for integrating the optimization methods into service-oriented infrastructures. However, a systematic study on inference engines is still lacking. This paper provides a comprehensive evaluation of 25 open-source and commercial inference engines. We examine each inference engine in terms of ease-of-use, ease-of-deployment, general-purpose support, scalability, and suitability for throughput- and latency-aware computation. Furthermore, we explore the design goals of each inference engine by investigating the optimization techniques it supports. In addition, we assess the ecosystem maturity of open source inference engines and handle the performance and cost policy of commercial solutions. We outline future research directions that include support for complex LLM-based services, support of various hardware, and enhanced security, offering practical guidance to researchers and developers in selecting and designing optimized LLM inference engines. We also provide a public repository to continually track developments in this fast-evolving field: https://github.com/sihyeong/Awesome-LLM-Inference-Engine

Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. However, conventional task-specific adaptation approaches do not show simultaneous memory saving and inference speedup at deployment time. Practical compression techniques like quantization and pruning require dedicated hardware or kernel support to achieve measured inference speedup. We develop TrimLLM based on the layer-wise specialization phenomenon we empirically observed and verified on contemporary LLMs. TrimLLM reduces the depth of LLMs via progressive layer dropping. We show it retains LLMs' capacity in specific domains and achieves inference speedup irrespective of hardware and deep learning frameworks. We evaluated TrimLLM on LLMs of various sizes for inference; models adapted on medical, legal, and financial datasets all demonstrate 2.1-5.7times inference speedup on consumer GPUs and up to 3.1times speedup on A100 when compared to state-of-the-art model compression algorithms, with no loss in accuracy at 50sim60\% model compression ratio.

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than the number of generated tokens. Hence, we explore inference-time hyper-scaling: by compressing the KV cache, we can generate more tokens within the same compute budget and further improve the accuracy of scaled inference. The success of this approach, however, hinges on the ability of compression methods to preserve accuracy even at high compression ratios. To make hyper-scaling practical, we introduce Dynamic Memory Sparsification (DMS), a novel method for sparsifying KV caches that only requires 1K training steps to achieve 8times compression, while maintaining better accuracy than training-free sparse attention. Instead of prematurely discarding cached tokens, DMS delays token eviction, implicitly merging representations and preserving critical information. We demonstrate the effectiveness of inference-time hyper-scaling with DMS on multiple families of LLMs, showing that it boosts accuracy for comparable inference runtime and memory load. For instance, we enhance Qwen-R1 32B by an average of 9.1 points on AIME 24, 7.6 on GPQA, and 9.6 on LiveCodeBench across compute budgets.

The emergence of large-scale Mixture of Experts (MoE) models has marked a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, the deployment and inference of these models present substantial challenges in terms of computational resources, latency, and energy efficiency. This comprehensive survey systematically analyzes the current landscape of inference optimization techniques for MoE models across the entire system stack. We first establish a taxonomical framework that categorizes optimization approaches into model-level, system-level, and hardware-level optimizations. At the model level, we examine architectural innovations including efficient expert design, attention mechanisms, various compression techniques such as pruning, quantization, and knowledge distillation, as well as algorithm improvement including dynamic routing strategies and expert merging methods. At the system level, we investigate distributed computing approaches, load balancing mechanisms, and efficient scheduling algorithms that enable scalable deployment. Furthermore, we delve into hardware-specific optimizations and co-design strategies that maximize throughput and energy efficiency. This survey not only provides a structured overview of existing solutions but also identifies key challenges and promising research directions in MoE inference optimization. Our comprehensive analysis serves as a valuable resource for researchers and practitioners working on large-scale deployment of MoE models in resource-constrained environments. To facilitate ongoing updates and the sharing of cutting-edge advances in MoE inference optimization research, we have established a repository accessible at https://github.com/MoE-Inf/awesome-moe-inference/.

Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alternative methods to improve model capabilities, particularly in tasks requiring advanced reasoning. Large reasoning models, which leverage long chain-of-thoughts, bring unprecedented breakthroughs in problem-solving capabilities but at a substantial deployment cost associated to longer generations. Reducing inference costs is crucial for the economic feasibility, user experience, and environmental sustainability of these models. In this work, we propose to train large reasoning models to reason efficiently. More precisely, we use reinforcement learning (RL) to train reasoning models to dynamically allocate inference-time compute based on task complexity. Our method incentivizes models to minimize unnecessary computational overhead while maintaining accuracy, thereby achieving substantial efficiency gains. It enables the derivation of a family of reasoning models with varying efficiency levels, controlled via a single hyperparameter. Experiments on two open-weight large reasoning models demonstrate significant reductions in inference cost while preserving most of the accuracy.

Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry. When GPU hardware resources are limited, we can explore alternative options on CPUs. To mitigate the financial burden and alleviate constraints imposed by hardware resources, optimizing inference performance is necessary. In this paper, we introduce an easily deployable inference performance optimization solution aimed at accelerating LLMs on CPUs. In this solution, we implement an effective way to reduce the KV cache size while ensuring precision. We propose a distributed inference optimization approach and implement it based on oneAPI Collective Communications Library. Furthermore, we propose optimization approaches for LLMs on CPU, and conduct tailored optimizations for the most commonly used models. The code is open-sourced at https://github.com/intel/xFasterTransformer.

The recent surge of open-source large language models (LLMs) enables developers to create AI-based solutions while maintaining control over aspects such as privacy and compliance, thereby providing governance and ownership of the model deployment process. To utilize these LLMs, inference engines are needed. These engines load the model's weights onto available resources, such as GPUs, and process queries to generate responses. The speed of inference, or performance, of the LLM, is critical for real-time applications, as it computes millions or billions of floating point operations per inference. Recently, advanced inference engines such as vLLM have emerged, incorporating novel mechanisms such as efficient memory management to achieve state-of-the-art performance. In this paper, we analyze the performance, particularly the throughput (tokens generated per unit of time), of 20 LLMs using two inference libraries: vLLM and HuggingFace's pipelines. We investigate how various hyperparameters, which developers must configure, influence inference performance. Our results reveal that throughput landscapes are irregular, with distinct peaks, highlighting the importance of hyperparameter optimization to achieve maximum performance. We also show that applying hyperparameter optimization when upgrading or downgrading the GPU model used for inference can improve throughput from HuggingFace pipelines by an average of 9.16% and 13.7%, respectively.

Inference-time optimization scales computation to derive deliberate reasoning steps for effective performance. While previous search-based strategies address the short-sightedness of auto-regressive generation, the vast search space leads to excessive exploration and insufficient exploitation. To strike an efficient balance to derive the optimal step, we frame the decoding strategy as foresight sampling, leveraging simulated future steps to obtain globally optimal step estimation. Built on it, we propose a novel decoding strategy, named phi-Decoding. To provide a precise and expressive estimation of step value, phi-Decoding approximates two distributions via foresight and clustering. Sampling from the joint distribution, the optimal steps can be selected for exploitation. To support adaptive computation allocation, we propose in-width and in-depth pruning strategies, featuring a light-weight solution to achieve inference efficiency. Extensive experiments across seven benchmarks show phi-Decoding outperforms strong baselines in both performance and efficiency. Additional analysis demonstrates its generalization across various LLMs and scalability across a wide range of computing budgets. The code will be released at https://github.com/xufangzhi/phi-Decoding, and the open-source PyPI package is coming soon.

Recent innovation in large language models (LLMs), and their myriad use-cases have rapidly driven up the compute capacity demand for datacenter GPUs. Several cloud providers and other enterprises have made substantial plans of growth in their datacenters to support these new workloads. One of the key bottleneck resources in datacenters is power, and given the increasing model sizes of LLMs, they are becoming increasingly power intensive. In this paper, we show that there is a significant opportunity to oversubscribe power in LLM clusters. Power oversubscription improves the power efficiency of these datacenters, allowing more deployable servers per datacenter, and reduces the deployment time, since building new datacenters is slow. We extensively characterize the power consumption patterns of a variety of LLMs and their configurations. We identify the differences between the inference and training power consumption patterns. Based on our analysis of these LLMs, we claim that the average and peak power utilization in LLM clusters for inference should not be very high. Our deductions align with the data from production LLM clusters, revealing that inference workloads offer substantial headroom for power oversubscription. However, the stringent set of telemetry and controls that GPUs offer in a virtualized environment, makes it challenging to have a reliable and robust power oversubscription mechanism. We propose POLCA, our framework for power oversubscription that is robust, reliable, and readily deployable for GPU clusters. Using open-source models to replicate the power patterns observed in production, we simulate POLCA and demonstrate that we can deploy 30% more servers in the same GPU cluster for inference, with minimal performance loss

This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key underlying the design of PowerInfer is exploiting the high locality inherent in LLM inference, characterized by a power-law distribution in neuron activation. This distribution indicates that a small subset of neurons, termed hot neurons, are consistently activated across inputs, while the majority, cold neurons, vary based on specific inputs. PowerInfer exploits such an insight to design a GPU-CPU hybrid inference engine: hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons are computed on the CPU, thus significantly reducing GPU memory demands and CPU-GPU data transfers. PowerInfer further integrates adaptive predictors and neuron-aware sparse operators, optimizing the efficiency of neuron activation and computational sparsity. Evaluation shows that PowerInfer attains an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs (including OPT-175B) on a single NVIDIA RTX 4090 GPU, only 18% lower than that achieved by a top-tier server-grade A100 GPU. This significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy.

The subject of green AI has been gaining attention within the deep learning community given the recent trend of ever larger and more complex neural network models. Existing solutions for reducing the computational load of training at inference time usually involve pruning the network parameters. Pruning schemes often create extra overhead either by iterative training and fine-tuning for static pruning or repeated computation of a dynamic pruning graph. We propose a new parameter pruning strategy for learning a lighter-weight sub-network that minimizes the energy cost while maintaining comparable performance to the fully parameterised network on given downstream tasks. Our proposed pruning scheme is green-oriented, as it only requires a one-off training to discover the optimal static sub-networks by dynamic pruning methods. The pruning scheme consists of a binary gating module and a novel loss function to uncover sub-networks with user-defined sparsity. Our method enables pruning and training simultaneously, which saves energy in both the training and inference phases and avoids extra computational overhead from gating modules at inference time. Our results on CIFAR-10 and CIFAR-100 suggest that our scheme can remove 50% of connections in deep networks with less than 1% reduction in classification accuracy. Compared to other related pruning methods, our method demonstrates a lower drop in accuracy for equivalent reductions in computational cost.

The performance of neural networks improves when more parameters are used. However, the model sizes are constrained by the available on-device memory during training and inference. Although applying techniques like quantization can alleviate the constraint, they suffer from performance degradation. In this work, we introduce NeuZip, a new weight compression scheme based on the entropy of floating-point numbers in neural networks. With NeuZip, we are able to achieve memory-efficient training and inference without sacrificing performance. Notably, we significantly reduce the memory footprint of training a Llama-3 8B model from 31GB to less than 16GB, while keeping the training dynamics fully unchanged. In inference, our method can reduce memory usage by more than half while maintaining near-lossless performance. Our code is publicly available.

Inference-time scaling has emerged as a powerful alternative to parameter scaling for improving language model performance on complex reasoning tasks. While existing methods have shown strong performance gains under fixed compute budgets, there has been little focus on optimally utilizing that budget during inference. In this work, we introduce A*-decoding, a search-based inference-time strategy that builds on the A* search algorithm to optimally utilize a fixed compute budget by prioritizing high-quality reasoning paths during generation. We frame language model decoding as a structured search in a state space of partial solutions, applying the A* transition model to identify promising continuations guided by an external process supervision signal. In our experiments, A*-decoding reaches the performance levels of strong inference scaling baselines like best-of-N and particle filtering while using up to 3x fewer tokens and 30% fewer PRM passes under equivalent compute budgets. On the MATH500 and AIME 2024 benchmarks, A*-decoding enables Llama-3.2-1B-Instruct to match the performance of the 70x larger Llama-3.1-70B-Instruct, and allows Qwen3-1.7B to reach o1-like reasoning accuracy. These results highlight the power of structured search in decoding, offering an alternative to brute-force sampling or scale-driven gains. Our work demonstrates how thoughtful inference-time strategies can enhance reasoning in SLMs, pointing toward future advances in more efficient and scalable language model deployment.

Large Language Models (LLMs) have achieved great success in solving difficult tasks across many domains, but such success comes with a high computation cost, and inference latency. As developers and third parties customize these models, the need to provide efficient inference has increased. Many efforts have attempted to reduce inference cost through model compression techniques such as pruning and distillation. However, these techniques either require labeled data, or are time-consuming as they require the compressed model to be retrained to regain accuracy. In this paper, we propose a gradient-free structured pruning framework that uses only unlabeled data. An evaluation on the GLUE and SQuAD benchmarks using BERT_{BASE} and DistilBERT illustrates the effectiveness of the proposed approach. By only using the weights of the pre-trained model and unlabeled data, in a matter of a few minutes on a single GPU, up to 40% of the original FLOP count can be reduced with less than a 4% accuracy loss across all tasks considered.

This work focuses on reducing neural network size, which is a major driver of neural network execution time, power consumption, bandwidth, and memory footprint. A key challenge is to reduce size in a manner that can be exploited readily for efficient training and inference without the need for specialized hardware. We propose Self-Compression: a simple, general method that simultaneously achieves two goals: (1) removing redundant weights, and (2) reducing the number of bits required to represent the remaining weights. This is achieved using a generalized loss function to minimize overall network size. In our experiments we demonstrate floating point accuracy with as few as 3% of the bits and 18% of the weights remaining in the network.

With the advancement of large language models (LLMs), solving complex reasoning tasks has gained increasing attention. Inference-time computation methods (e.g., Best-of-N, beam search, et al.) are particularly valuable as they can enhance reasoning performance without modifying model parameters or requiring additional training. However, these techniques come with implementation challenges, and most existing methods remain at the proof-of-concept stage with limited practical adoption due to their computational complexity and varying effectiveness across different tasks. In this paper, we investigate and benchmark diverse inference-time computation strategies across reasoning tasks of varying complexity. Since most current methods rely on a proposer-verifier pipeline that first generates candidate solutions (e.g., reasoning solutions) and then selects the best one based on reward signals (e.g., RLHF rewards, process rewards), our research focuses on optimizing both candidate solution generation (e.g., instructing prompts, hyperparameters such as temperature and top-p) and reward mechanisms (e.g., self-evaluation, reward types). Through extensive experiments (more than 20,000 A100-80G GPU hours with over 1,000 experiments) across a variety of models (e.g., Llama, Qwen, and Mistral families) of various sizes, our ablation studies reveal that previously overlooked strategies can significantly enhance performance (e.g., tuning temperature can improve reasoning task performance by up to 5%). Furthermore, we establish a standardized benchmark for inference-time computation by systematically evaluating six representative methods across eight reasoning tasks. These findings provide a stronger foundation for future research. The code is available at https://github.com/usail-hkust/benchmark_inference_time_computation_LLM

Recently, Zaremba et al. demonstrated that increasing inference-time computation improves robustness in large proprietary reasoning LLMs. In this paper, we first show that smaller-scale, open-source models (e.g., DeepSeek R1, Qwen3, Phi-reasoning) can also benefit from inference-time scaling using a simple budget forcing strategy. More importantly, we reveal and critically examine an implicit assumption in prior work: intermediate reasoning steps are hidden from adversaries. By relaxing this assumption, we identify an important security risk, intuitively motivated and empirically verified as an inverse scaling law: if intermediate reasoning steps become explicitly accessible, increased inference-time computation consistently reduces model robustness. Finally, we discuss practical scenarios where models with hidden reasoning chains are still vulnerable to attacks, such as models with tool-integrated reasoning and advanced reasoning extraction attacks. Our findings collectively demonstrate that the robustness benefits of inference-time scaling depend heavily on the adversarial setting and deployment context. We urge practitioners to carefully weigh these subtle trade-offs before applying inference-time scaling in security-sensitive, real-world applications.

We examine the reasoning and planning capabilities of large language models (LLMs) in solving complex tasks. Recent advances in inference-time techniques demonstrate the potential to enhance LLM reasoning without additional training by exploring intermediate steps during inference. Notably, OpenAI's o1 model shows promising performance through its novel use of multi-step reasoning and verification. Here, we explore how scaling inference-time techniques can improve reasoning and planning, focusing on understanding the tradeoff between computational cost and performance. To this end, we construct a comprehensive benchmark, known as Sys2Bench, and perform extensive experiments evaluating existing inference-time techniques on eleven diverse tasks across five categories, including arithmetic reasoning, logical reasoning, common sense reasoning, algorithmic reasoning, and planning. Our findings indicate that simply scaling inference-time computation has limitations, as no single inference-time technique consistently performs well across all reasoning and planning tasks.

Scaling the amount of compute used to train language models has dramatically improved their capabilities. However, when it comes to inference, we often limit the amount of compute to only one attempt per problem. Here, we explore inference compute as another axis for scaling by increasing the number of generated samples. Across multiple tasks and models, we observe that coverage - the fraction of problems solved by any attempt - scales with the number of samples over four orders of magnitude. In domains like coding and formal proofs, where all answers can be automatically verified, these increases in coverage directly translate into improved performance. When we apply repeated sampling to SWE-bench Lite, the fraction of issues solved with DeepSeek-V2-Coder-Instruct increases from 15.9% with one sample to 56% with 250 samples, outperforming the single-attempt state-of-the-art of 43% which uses more capable frontier models. Moreover, using current API pricing, amplifying the cheaper DeepSeek model with five samples is more cost-effective and solves more issues than paying a premium for one sample from GPT-4o or Claude 3.5 Sonnet. Interestingly, the relationship between coverage and the number of samples is often log-linear and can be modelled with an exponentiated power law, suggesting the existence of inference-time scaling laws. Finally, we find that identifying correct samples out of many generations remains an important direction for future research in domains without automatic verifiers. When solving math word problems from GSM8K and MATH, coverage with Llama-3 models grows to over 95% with 10,000 samples. However, common methods to pick correct solutions from a sample collection, such as majority voting or reward models, plateau beyond several hundred samples and fail to fully scale with the sample budget.

Sampling is a basic operation in many inference-time algorithms of large language models (LLMs). To scale up inference efficiently with a limited compute, it is crucial to find an optimal allocation for sample compute budgets: Which sampling configurations (model, temperature, language, etc.) do we use? How many samples do we generate in each configuration? We formulate these choices as a learning problem and propose OSCA, an algorithm that Optimizes Sample Compute Allocation by finding an optimal mix of different inference configurations. Our experiments show that with our learned mixed allocation, we can achieve accuracy better than the best single configuration with 128x less compute on code generation and 25x less compute on 4 reasoning tasks. OSCA is also shown to be effective in agentic workflows beyond single-turn tasks, achieving a better accuracy on SWE-Bench with 3x less compute than the default configuration. Our code and generations are released at https://github.com/LeiLiLab/OSCA.

Large language models (LLMs) have achieved significant performance gains via scaling up model sizes and/or data. However, recent evidence suggests diminishing returns from such approaches, motivating scaling the computation spent at inference time. Existing inference-time scaling methods, usually with reward models, cast the task as a search problem, which tends to be vulnerable to reward hacking as a consequence of approximation errors in reward models. In this paper, we instead cast inference-time scaling as a probabilistic inference task and leverage sampling-based techniques to explore the typical set of the state distribution of a state-space model with an approximate likelihood, rather than optimize for its mode directly. We propose a novel inference-time scaling approach by adapting particle-based Monte Carlo methods to this task. Our empirical evaluation demonstrates that our methods have a 4-16x better scaling rate over our deterministic search counterparts on various challenging mathematical reasoning tasks. Using our approach, we show that Qwen2.5-Math-1.5B-Instruct can surpass GPT-4o accuracy in only 4 rollouts, while Qwen2.5-Math-7B-Instruct scales to o1 level accuracy in only 32 rollouts. Our work not only presents an effective method to inference-time scaling, but also connects the rich literature in probabilistic inference with inference-time scaling of LLMs to develop more robust algorithms in future work. Code and further information is available at https://probabilistic-inference-scaling.github.io.

Recent innovations in generative large language models (LLMs) have made their applications and use-cases ubiquitous. This has led to large-scale deployments of these models, using complex, expensive, and power-hungry AI accelerators, most commonly GPUs. These developments make LLM inference efficiency an important challenge. Based on our extensive characterization, we find that there are two main phases during an LLM inference request: a compute-intensive prompt computation, and a memory-intensive token generation, each with distinct latency, throughput, memory, and power characteristics. Despite state-of-the-art batching and scheduling, the token generation phase underutilizes compute resources. Specifically, unlike compute-intensive prompt computation phases, token generation phases do not require the compute capability of the latest GPUs, and can be run with lower power and cost. With Splitwise, we propose splitting the two phases of a LLM inference request on to separate machines. This allows us to use hardware that is well-suited for each phase, and provision resources independently per phase. However, splitting an inference request across machines requires state transfer from the machine running prompt computation over to the machine generating tokens. We implement and optimize this state transfer using the fast back-plane interconnects available in today's GPU clusters. We use the Splitwise technique to design LLM inference clusters using the same or different types of machines for the prompt computation and token generation phases. Our clusters are optimized for three key objectives: throughput, cost, and power. In particular, we show that we can achieve 1.4x higher throughput at 20% lower cost than current designs. Alternatively, we can achieve 2.35x more throughput with the same cost and power budgets.

Inference accounts for the majority of latency and energy consumption in large language model (LLM) deployments, often exceeding 90% of total cost. While training-time efficiency has seen extensive progress, runtime optimization remains a key bottleneck, particularly under autoregressive decoding. Existing approaches -- such as pruning, quantization, early exits, and speculative decoding -- often require retraining, architectural changes, or disrupt decoding compatibility. We introduce QuickSilver, a modular, token-level framework that enables semantic adaptivity at inference time without altering model weights or structure. QuickSilver integrates four synergistic mechanisms: (i) Dynamic Token Halting, which halts computation for tokens with converged representations; (ii) KV Cache Skipping, which selectively suppresses memory writes to reduce attention overhead; and (iii) Contextual Token Fusion, which collapses redundant tokens into shared paths to shrink sequence length. Unlike speculative decoding or MoE routing, QuickSilver operates entirely on frozen, dense models and requires no auxiliary networks. Applied to GPT-2 and Llama-2 across WikiText-103 and C4, QuickSilver achieves up to 39.6% FLOP reduction with negligible perplexity degradation (<=0.2).

Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them inaccessible to most researchers. In this work, we investigate methods for cost-efficient inference and fine-tuning of LLMs, comparing local and distributed strategies. We observe that a large enough model (50B+) can run efficiently even on geodistributed devices in a consumer-grade network. This could allow running LLM efficiently by pooling together idle compute resources of multiple research groups and volunteers. We address two open problems: (1) how to perform inference and fine-tuning reliably if any device can disconnect abruptly and (2) how to partition LLMs between devices with uneven hardware, joining and leaving at will. In order to do that, we develop special fault-tolerant inference algorithms and load-balancing protocols that automatically assign devices to maximize the total system throughput. We showcase these algorithms in Petals - a decentralized system that runs Llama 2 (70B) and BLOOM (176B) over the Internet up to 10x faster than offloading for interactive generation. We evaluate the performance of our system in simulated conditions and a real-world setup spanning two continents.

While 4-bit quantization has emerged as a memory-optimal choice for non-reasoning models and zero-shot tasks across scales, we show that this universal prescription fails for reasoning models, where the KV cache rather than model size can dominate memory. Through systematic experiments across 1,700 inference scenarios on AIME25 and GPQA-Diamond, we find a scale-dependent trade-off: models with an effective size below 8-bit 4B parameters achieve better accuracy by allocating memory to more weights rather than longer generation, while larger models achieve better accuracy by allocating memory to longer generations. This scale threshold also determines when parallel scaling becomes memory-efficient and whether KV cache eviction outperforms KV quantization. Our findings show that memory optimization for LLMs cannot be scale-agnostic, while providing principled guidelines: for small reasoning models, prioritize model capacity over test-time compute, while for larger ones, maximize test-time compute. Our results suggest that optimizing reasoning models for deployment requires fundamentally different strategies from those established for non-reasoning models.

With the blossom of large language models (LLMs), inference efficiency becomes increasingly important. Various approximation methods are proposed to reduce the cost at inference time. Contextual Sparsity (CS) is appealing for its training-free nature and its ability to reach a higher compression ratio seemingly without quality degradation. However, after a comprehensive evaluation of contextual sparsity methods on various complex generation tasks, we find that although CS succeeds in prompt-understanding tasks, CS significantly degrades the model performance for reasoning, deduction, and knowledge-based tasks. Despite the gap in end-to-end accuracy, we observed that sparse models often share general problem-solving logic and require only a few token corrections to recover the original model performance. This paper introduces Sirius, an efficient correction mechanism, which significantly recovers CS models quality on reasoning tasks while maintaining its efficiency gain. Sirius is evaluated on 6 models with 8 difficult generation tasks in reasoning, math, and coding and shows consistent effectiveness and efficiency. Also, we carefully develop a system implementation for Sirius and show that Sirius achieves roughly 20% reduction in latency for 8B model on-chip and 35% reduction for 70B model offloading. We open-source our implementation of Sirius at https://github.com/Infini-AI-Lab/Sirius.git.

Accelerating the inference of large language models (LLMs) is an important challenge in artificial intelligence. This paper introduces distributed speculative inference (DSI), a novel distributed inference algorithm that is provably faster than speculative inference (SI) [leviathan2023fast, chen2023accelerating, miao2023specinfer] and traditional autoregressive inference (non-SI). Like other SI algorithms, DSI works on frozen LLMs, requiring no training or architectural modifications, and it preserves the target distribution. Prior studies on SI have demonstrated empirical speedups (compared to non-SI) but require a fast and accurate drafter LLM. In practice, off-the-shelf LLMs often do not have matching drafters that are sufficiently fast and accurate. We show a gap: SI gets slower than non-SI when using slower or less accurate drafters. We close this gap by proving that DSI is faster than both SI and non-SI given any drafters. By orchestrating multiple instances of the target and drafters, DSI is not only faster than SI but also supports LLMs that cannot be accelerated with SI. Our simulations show speedups of off-the-shelf LLMs in realistic settings: DSI is 1.29-1.92x faster than SI.

The large number of parameters in Pretrained Language Models enhance their performance, but also make them resource-intensive, making it challenging to deploy them on commodity hardware like a single GPU. Due to the memory and power limitations of these devices, model compression techniques are often used to decrease both the model's size and its inference latency. This usually results in a trade-off between model accuracy and efficiency. Therefore, optimizing this balance is essential for effectively deploying LLMs on commodity hardware. A significant portion of the efficiency challenge is the Feed-forward network (FFN) component, which accounts for roughly 2{3} total parameters and inference latency. In this paper, we first observe that only a few neurons of FFN module have large output norm for any input tokens, a.k.a. heavy hitters, while the others are sparsely triggered by different tokens. Based on this observation, we explicitly split the FFN into two parts according to the heavy hitters. We improve the efficiency-accuracy trade-off of existing compression methods by allocating more resource to FFN parts with heavy hitters. In practice, our method can reduce model size by 43.1\% and bring 1.25sim1.56times wall clock time speedup on different hardware with negligible accuracy drop.

Large language models (LLMs) excel in most NLP tasks but also require expensive cloud servers for deployment due to their size, while smaller models that can be deployed on lower cost (e.g., edge) devices, tend to lag behind in terms of response quality. Therefore in this work we propose a hybrid inference approach which combines their respective strengths to save cost and maintain quality. Our approach uses a router that assigns queries to the small or large model based on the predicted query difficulty and the desired quality level. The desired quality level can be tuned dynamically at test time to seamlessly trade quality for cost as per the scenario requirements. In experiments our approach allows us to make up to 40% fewer calls to the large model, with no drop in response quality.

Large Language Models (LLMs) have revolutionized natural language processing by achieving state-of-the-art results across a variety of tasks. However, the computational demands of LLM inference, including high memory consumption and slow processing speeds, pose significant challenges for real-world applications, particularly on resource-constrained devices. Efficient inference is crucial for scaling the deployment of LLMs to a broader range of platforms, including mobile and edge devices. This survey explores contemporary techniques in model compression that address these challenges by reducing the size and computational requirements of LLMs while maintaining their performance. We focus on model-level compression methods, including quantization, knowledge distillation, and pruning, as well as system-level optimizations like KV cache efficient design. Each of these methodologies offers a unique approach to optimizing LLMs, from reducing numerical precision to transferring knowledge between models and structurally simplifying neural networks. Additionally, we discuss emerging trends in system-level design that further enhance the efficiency of LLM inference. This survey aims to provide a comprehensive overview of current advancements in model compression and their potential to make LLMs more accessible and practical for diverse applications.

Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning. Test-time scaling methods, such as prolonging CoT with explicit token-level exploration, can push LRMs' accuracy boundaries, but they incur significant decoding overhead. A key inefficiency source is LRMs often generate redundant thinking CoTs, which demonstrate clear structured overthinking and underthinking patterns. Inspired by human cognitive reasoning processes and numerical optimization theories, we propose TrimR, a verifier-based, training-free, efficient framework for dynamic CoT compression to trim reasoning and enhance test-time scaling, explicitly tailored for production-level deployment. Our method employs a lightweight, pretrained, instruction-tuned verifier to detect and truncate redundant intermediate thoughts of LRMs without any LRM or verifier fine-tuning. We present both the core algorithm and asynchronous online system engineered for high-throughput industrial applications. Empirical evaluations on Ascend NPUs and vLLM show that our framework delivers substantial gains in inference efficiency under large-batch workloads. In particular, on the four MATH500, AIME24, AIME25, and GPQA benchmarks, the reasoning runtime of Pangu Pro MoE, Pangu-R-38B, QwQ-32B, and DeepSeek-R1-Distill-Qwen-32B is improved by up to 70% with negligible impact on accuracy.

The scaling of inference computation has unlocked the potential of long-context large language models (LLMs) across diverse settings. For knowledge-intensive tasks, the increased compute is often allocated to incorporate more external knowledge. However, without effectively utilizing such knowledge, solely expanding context does not always enhance performance. In this work, we investigate inference scaling for retrieval augmented generation (RAG), exploring strategies beyond simply increasing the quantity of knowledge. We focus on two inference scaling strategies: in-context learning and iterative prompting. These strategies provide additional flexibility to scale test-time computation (e.g., by increasing retrieved documents or generation steps), thereby enhancing LLMs' ability to effectively acquire and utilize contextual information. We address two key questions: (1) How does RAG performance benefit from the scaling of inference computation when optimally configured? (2) Can we predict the optimal test-time compute allocation for a given budget by modeling the relationship between RAG performance and inference parameters? Our observations reveal that increasing inference computation leads to nearly linear gains in RAG performance when optimally allocated, a relationship we describe as the inference scaling laws for RAG. Building on this, we further develop the computation allocation model to estimate RAG performance across different inference configurations. The model predicts optimal inference parameters under various computation constraints, which align closely with the experimental results. By applying these optimal configurations, we demonstrate that scaling inference compute on long-context LLMs achieves up to 58.9% gains on benchmark datasets compared to standard RAG.

Reasoning models have demonstrated impressive performance in self-reflection and chain-of-thought reasoning. However, they often produce excessively long outputs, leading to prohibitively large key-value (KV) caches during inference. While chain-of-thought inference significantly improves performance on complex reasoning tasks, it can also lead to reasoning failures when deployed with existing KV cache compression approaches. To address this, we propose Redundancy-aware KV Cache Compression for Reasoning models (R-KV), a novel method specifically targeting redundant tokens in reasoning models. Our method preserves nearly 100% of the full KV cache performance using only 10% of the KV cache, substantially outperforming existing KV cache baselines, which reach only 60% of the performance. Remarkably, R-KV even achieves 105% of full KV cache performance with 16% of the KV cache. This KV-cache reduction also leads to a 90% memory saving and a 6.6X throughput over standard chain-of-thought reasoning inference. Experimental results show that R-KV consistently outperforms existing KV cache compression baselines across two mathematical reasoning datasets.

Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks at the cost of only a marginal loss in accuracy and achieve a sizable reduction in model size. This hints at the possibility that the baseline models in these experiments are perhaps severely over-parameterized at the outset and a viable alternative for model compression might be to simply reduce the number of hidden units while maintaining the model's dense connection structure, exposing a similar trade-off in model size and accuracy. We investigate these two distinct paths for model compression within the context of energy-efficient inference in resource-constrained environments and propose a new gradual pruning technique that is simple and straightforward to apply across a variety of models/datasets with minimal tuning and can be seamlessly incorporated within the training process. We compare the accuracy of large, but pruned models (large-sparse) and their smaller, but dense (small-dense) counterparts with identical memory footprint. Across a broad range of neural network architectures (deep CNNs, stacked LSTM, and seq2seq LSTM models), we find large-sparse models to consistently outperform small-dense models and achieve up to 10x reduction in number of non-zero parameters with minimal loss in accuracy.

It is commonly believed that scaling language models should commit a significant space or time cost, by increasing the parameters (parameter scaling) or output tokens (inference-time scaling). We introduce the third and more inference-efficient scaling paradigm: increasing the model's parallel computation during both training and inference time. We apply P diverse and learnable transformations to the input, execute forward passes of the model in parallel, and dynamically aggregate the P outputs. This method, namely parallel scaling (ParScale), scales parallel computation by reusing existing parameters and can be applied to any model structure, optimization procedure, data, or task. We theoretically propose a new scaling law and validate it through large-scale pre-training, which shows that a model with P parallel streams is similar to scaling the parameters by O(log P) while showing superior inference efficiency. For example, ParScale can use up to 22times less memory increase and 6times less latency increase compared to parameter scaling that achieves the same performance improvement. It can also recycle an off-the-shelf pre-trained model into a parallelly scaled one by post-training on a small amount of tokens, further reducing the training budget. The new scaling law we discovered potentially facilitates the deployment of more powerful models in low-resource scenarios, and provides an alternative perspective for the role of computation in machine learning.

We conduct experiments on the impact of increasing inference-time compute in reasoning models (specifically OpenAI o1-preview and o1-mini) on their robustness to adversarial attacks. We find that across a variety of attacks, increased inference-time compute leads to improved robustness. In many cases (with important exceptions), the fraction of model samples where the attack succeeds tends to zero as the amount of test-time compute grows. We perform no adversarial training for the tasks we study, and we increase inference-time compute by simply allowing the models to spend more compute on reasoning, independently of the form of attack. Our results suggest that inference-time compute has the potential to improve adversarial robustness for Large Language Models. We also explore new attacks directed at reasoning models, as well as settings where inference-time compute does not improve reliability, and speculate on the reasons for these as well as ways to address them.

Inference-time computation is a powerful paradigm to enhance the performance of large language models (LLMs), with Best-of-N sampling being a widely used technique. However, this method is computationally expensive, requiring both (1) an external reward model and (2) the generation of multiple samples. In this work, we introduce a new generative self-evaluation scheme designed to adaptively reduce the number of generated samples while maintaining or even improving performance. We use a generative reward model formulation, allowing the LLM to predict mid-generation the probability that restarting the generation will yield a better response. These predictions are obtained without an external reward model and can be used to decide whether or not to generate more samples, prune unpromising samples early on, or to pick the best sample. This capability is very inexpensive as it involves generating a single predefined token. Trained using a dataset constructed with real unfiltered LMSYS user prompts, Llama 3.1 8B's win rate against GPT-4 on AlpacaEval increases from 21% to 34% with 16 samples and math performance on GSM8K improves from 84% to 91%. By sampling only when the LLM determines that it is beneficial to do so and adaptively adjusting temperature annealing, we demonstrate that 74% of the improvement from using 16 samples can be achieved with only 1.2 samples on average. We further demonstrate that 50-75% of samples can be pruned early in generation with minimal degradation in performance. Overall, our methods enable more efficient and scalable compute utilization during inference for LLMs.

Inference of Large Language Models (LLMs) across computer clusters has become a focal point of research in recent times, with many acceleration techniques taking inspiration from CPU speculative execution. These techniques reduce bottlenecks associated with memory bandwidth, but also increase end-to-end latency per inference run, requiring high speculation acceptance rates to improve performance. Combined with a variable rate of acceptance across tasks, speculative inference techniques can result in reduced performance. Additionally, pipeline-parallel designs require many user requests to maintain maximum utilization. As a remedy, we propose PipeInfer, a pipelined speculative acceleration technique to reduce inter-token latency and improve system utilization for single-request scenarios while also improving tolerance to low speculation acceptance rates and low-bandwidth interconnects. PipeInfer exhibits up to a 2.15times improvement in generation speed over standard speculative inference. PipeInfer achieves its improvement through Continuous Asynchronous Speculation and Early Inference Cancellation, the former improving latency and generation speed by running single-token inference simultaneously with several speculative runs, while the latter improves speed and latency by skipping the computation of invalidated runs, even in the middle of inference.

Large reasoning models (LRMs) have exhibited the capacity of enhancing reasoning performance via internal test-time scaling. Building upon this, a promising direction is to further scale test-time compute to unlock even greater reasoning capabilities. However, as we push these scaling boundaries, systematically understanding the practical limits and achieving optimal resource allocation becomes a critical challenge. In this paper, we investigate the scaling Pareto of test-time scaling and introduce the Test-Time Scaling Performance Model (TTSPM). We theoretically analyze two fundamental paradigms for such extended scaling, parallel scaling and sequential scaling, from a probabilistic modeling perspective. Our primary contribution is the derivation of the saturation point on the scaling budget for both strategies, identifying thresholds beyond which additional computation yields diminishing returns. Remarkably, despite their distinct mechanisms, both paradigms converge to a unified mathematical structure in their upper bounds. We empirically validate our theoretical findings on challenging reasoning benchmarks, including AIME, MATH-500, and GPQA, demonstrating the practical utility of these bounds for test-time resource allocation. We hope that this work provides insights into the cost-benefit trade-offs of test-time scaling, guiding the development of more resource-efficient inference strategies for large reasoning models.

Recent research has generated hope that inference scaling could allow weaker language models to match or exceed the accuracy of stronger models, such as by repeatedly sampling solutions to a coding problem until it passes unit tests. The central thesis of this paper is that there is no free lunch for inference scaling: indefinite accuracy improvement through resampling can only be realized if the "verifier" (in this case, a set of unit tests) is perfect. When the verifier is imperfect, as it almost always is in domains such as reasoning or coding (for example, unit tests have imperfect coverage), there is a nonzero probability of false positives: incorrect solutions that pass the verifier. Resampling cannot decrease this probability, so it imposes an upper bound to the accuracy of resampling-based inference scaling even with an infinite compute budget. We find that there is a very strong correlation between the model's single-sample accuracy (i.e. accuracy without unit tests) and its false positive rate on coding benchmarks HumanEval and MBPP, whose unit tests have limited coverage. Therefore, no amount of inference scaling of weaker models can enable them to match the single-sample accuracy of a sufficiently strong model (Fig. 1a). When we consider that false positives have a negative utility compared to abstaining from producing a solution, it bends the inference scaling curve further downward. Empirically, we find that the optimal number of samples can be less than 10 under realistic assumptions (Fig. 1b). Finally, we show that beyond accuracy, false positives may have other undesirable qualities, such as poor adherence to coding style conventions.

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory inference but often suffer from efficiency due to I/O bottlenecks. To achieve low-latency LLMs inference on resource-constrained devices, we introduce HeteGen, a novel approach that presents a principled framework for heterogeneous parallel computing using CPUs and GPUs. Based on this framework, HeteGen further employs heterogeneous parallel computing and asynchronous overlap for LLMs to mitigate I/O bottlenecks. Our experiments demonstrate a substantial improvement in inference speed, surpassing state-of-the-art methods by over 317% at most.

Inference-time scaling can enhance the reasoning capabilities of large language models (LLMs) on complex problems that benefit from step-by-step problem solving. Although lengthening generated scratchpads has proven effective for mathematical tasks, the broader impact of this approach on other tasks remains less clear. In this work, we investigate the benefits and limitations of scaling methods across nine state-of-the-art models and eight challenging tasks, including math and STEM reasoning, calendar planning, NP-hard problems, navigation, and spatial reasoning. We compare conventional models (e.g., GPT-4o) with models fine-tuned for inference-time scaling (e.g., o1) through evaluation protocols that involve repeated model calls, either independently or sequentially with feedback. These evaluations approximate lower and upper performance bounds and potential for future performance improvements for each model, whether through enhanced training or multi-model inference systems. Our extensive empirical analysis reveals that the advantages of inference-time scaling vary across tasks and diminish as problem complexity increases. In addition, simply using more tokens does not necessarily translate to higher accuracy in these challenging regimes. Results from multiple independent runs with conventional models using perfect verifiers show that, for some tasks, these models can achieve performance close to the average performance of today's most advanced reasoning models. However, for other tasks, a significant performance gap remains, even in very high scaling regimes. Encouragingly, all models demonstrate significant gains when inference is further scaled with perfect verifiers or strong feedback, suggesting ample potential for future improvements.

In real world, large language models (LLMs) can serve as the assistant to help users accomplish their jobs, and also support the development of advanced applications. For the wide application of LLMs, the inference efficiency is an essential concern, which has been widely studied in existing work, and numerous optimization algorithms and code libraries have been proposed to improve it. Nonetheless, users still find it challenging to compare the effectiveness of all the above methods and understand the underlying mechanisms. In this work, we perform a detailed coarse-to-fine analysis of the inference performance of various code libraries. To evaluate the overall effectiveness, we examine four usage scenarios within two practical applications. We further provide both theoretical and empirical fine-grained analyses of each module in the Transformer architecture. Our experiments yield comprehensive results that are invaluable for researchers to evaluate code libraries and improve inference strategies.

The Mixture of Experts (MoE) is an effective architecture for scaling large language models by leveraging sparse expert activation, optimizing the trade-off between performance and efficiency. However, under expert parallelism, MoE suffers from inference inefficiencies due to imbalanced token-to-expert assignment, where some experts are overloaded while others remain underutilized. This imbalance leads to poor resource utilization and increased latency, as the most burdened expert dictates the overall delay, a phenomenon we define as the \textit{Straggler Effect}. To mitigate this, we propose Capacity-Aware Inference, including two key techniques: (1) \textit{Capacity-Aware Token Drop}, which discards overloaded tokens to regulate the maximum latency of MoE, and (2) \textit{Capacity-Aware Token Reroute}, which reallocates overflowed tokens to underutilized experts, balancing the token distribution. These techniques collectively optimize both high-load and low-load expert utilization, leading to a more efficient MoE inference pipeline. Extensive experiments demonstrate the effectiveness of our methods, showing significant improvements in inference efficiency, e.g., 0.2\% average performance increase and a 1.94times inference speedup on Mixtral-8times7B-Instruct.

Recent reasoning-focused language models achieve high accuracy by generating lengthy intermediate reasoning paths before producing final answers. While this approach is effective in solving problems that require logical thinking, long reasoning paths significantly increase memory usage and throughput of token generation, limiting the practical deployment of such models. We propose Reasoning Path Compression (RPC), a training-free method that accelerates inference by leveraging the semantic sparsity of reasoning paths. RPC periodically compresses the KV cache by retaining KV cache that receive high importance score, which are computed using a selector window composed of recently generated queries. Experiments show that RPC improves generation throughput of QwQ-32B by up to 1.60times compared to the inference with full KV cache, with an accuracy drop of 1.2% on the AIME 2024 benchmark. Our findings demonstrate that semantic sparsity in reasoning traces can be effectively exploited for compression, offering a practical path toward efficient deployment of reasoning LLMs. Our code is available at https://github.com/jiwonsong-dev/ReasoningPathCompression.

Large Language Models (LLMs) have made significant strides in problem-solving by incorporating reasoning processes. However, this enhanced reasoning capability results in an increased number of output tokens during inference, leading to higher computational costs. To address this challenge, we propose TwT (Thinking without Tokens), a method that reduces inference-time costs through habitual reasoning distillation with multi-teachers' guidance, while maintaining high performance. Our approach introduces a Habitual Reasoning Distillation method, which internalizes explicit reasoning into the model's habitual behavior through a Teacher-Guided compression strategy inspired by human cognition. Additionally, we propose Dual-Criteria Rejection Sampling (DCRS), a technique that generates a high-quality and diverse distillation dataset using multiple teacher models, making our method suitable for unsupervised scenarios. Experimental results demonstrate that TwT effectively reduces inference costs while preserving superior performance, achieving up to a 13.6% improvement in accuracy with fewer output tokens compared to other distillation methods, offering a highly practical solution for efficient LLM deployment.

Large Language Models (LLMs) have demonstrated the ability to tackle increasingly complex tasks through advanced reasoning, long-form content generation, and tool use. Solving these tasks often involves long inference-time computations. In human problem solving, a common strategy to expedite work is collaboration: by dividing the problem into sub-tasks, exploring different strategies concurrently, etc. Recent research has shown that LLMs can also operate in parallel by implementing explicit cooperation frameworks, such as voting mechanisms or the explicit creation of independent sub-tasks that can be executed in parallel. However, each of these frameworks may not be suitable for all types of tasks, which can hinder their applicability. In this work, we propose a different design approach: we run LLM "workers" in parallel , allowing them to synchronize via a concurrently-updated attention cache and prompt these workers to decide how best to collaborate. Our approach allows the instances to come up with their own collaboration strategy for the problem at hand, all the while "seeing" each other's partial progress in the concurrent cache. We implement this approach via Hogwild! Inference: a parallel LLM inference engine where multiple instances of the same LLM run in parallel with the same attention cache, with "instant" access to each other's generated tokens. Hogwild! inference takes advantage of Rotary Position Embeddings (RoPE) to avoid recomputation while improving parallel hardware utilization. We find that modern reasoning-capable LLMs can perform inference with shared Key-Value cache out of the box, without additional fine-tuning.

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass Large Language Model, an innovative architecture that extends the core decoder-only framework by incorporating subsampling, upsampling, and bypass modules. The subsampling modules are responsible for shortening the sequence, while the upsampling modules restore the sequence length, and the bypass modules enhance convergence. In comparison to LLaMA, the proposed SUBLLM exhibits significant enhancements in both training and inference speeds as well as memory usage, while maintaining competitive few-shot performance. During training, SUBLLM increases speeds by 26% and cuts memory by 10GB per GPU. In inference, it boosts speeds by up to 37% and reduces memory by 1GB per GPU. The training and inference speeds can be enhanced by 34% and 52% respectively when the context window is expanded to 8192. Our code is available at https://github.com/XiaoMi/subllm.

Large language models have become the cornerstone of natural language processing, but their use comes with substantial costs in terms of compute and memory resources. Sparsification provides a solution to alleviate these resource constraints, and recent works have shown that trained models can be sparsified post-hoc. Existing sparsification techniques face challenges as they need additional data structures and offer constrained speedup with current hardware. In this paper we present SliceGPT, a new post-training sparsification scheme which replaces each weight matrix with a smaller (dense) matrix, reducing the embedding dimension of the network. Through extensive experimentation, we show that SliceGPT can remove up to 25% of the model parameters (including embeddings) for LLAMA2-70B, OPT 66B and Phi-2 models while maintaining 99%, 99% and 90% zero-shot task performance of the dense model respectively. Our sliced models run on fewer GPUs and run faster without any additional code optimization: on 24GB consumer GPUs we reduce the total compute for inference on LLAMA2-70B to 64% of that of the dense model; on 40GB A100 GPUs we reduce it to 66%. We offer a new insight, computational invariance in transformer networks, which enables SliceGPT and we hope it will inspire and enable future avenues to reduce memory and computation demands for pre-trained models. Code is available at: https://github.com/microsoft/TransformerCompression

The application of Transformer-based large models has achieved numerous success in recent years. However, the exponential growth in the parameters of large models introduces formidable memory challenge for edge deployment. Prior works to address this challenge mainly focus on optimizing the model structure and adopting memory swapping methods. However, the former reduces the inference accuracy, and the latter raises the inference latency. This paper introduces PIPELOAD, a novel memory-efficient pipeline execution mechanism. It reduces memory usage by incorporating dynamic memory management and minimizes inference latency by employing parallel model loading. Based on PIPELOAD mechanism, we present Hermes, a framework optimized for large model inference on edge devices. We evaluate Hermes on Transformer-based models of different sizes. Our experiments illustrate that Hermes achieves up to 4.24 X increase in inference speed and 86.7% lower memory consumption than the state-of-the-art pipeline mechanism for BERT and ViT models, 2.58 X increase in inference speed and 90.3% lower memory consumption for GPT-style models.

Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP), attaining substantial performance gains through widely adopted test-time scaling strategies, notably reflective Chain-of-Thought (CoT) reasoning and increased sampling passes. However, they both introduce significant computational overhead for inference. Moreover, existing cost analyses typically regulate only the number of sampling passes, while neglecting the substantial disparities in sampling costs introduced by different scaling strategies. In this paper, we systematically compare the efficiency of different test-time scaling strategies for ATP models and demonstrate the inefficiency of the current state-of-the-art (SOTA) open-source approaches. We then investigate approaches to significantly reduce token usage and sample passes while maintaining the original performance. Specifically, we propose two complementary methods that can be integrated into a unified EconRL pipeline for amplified benefits: (1) a dynamic Chain-of-Thought (CoT) switching mechanism designed to mitigate unnecessary token consumption, and (2) Diverse parallel-scaled reinforcement learning (RL) with trainable prefixes to enhance pass rates under constrained sampling passes. Experiments on miniF2F and ProofNet demonstrate that our EconProver achieves comparable performance to baseline methods with only 12% of the computational cost. This work provides actionable insights for deploying lightweight ATP models without sacrificing performance.

We propose a new localized inference algorithm for answering marginalization queries in large graphical models with the correlation decay property. Given a query variable and a large graphical model, we define a much smaller model in a local region around the query variable in the target model so that the marginal distribution of the query variable can be accurately approximated. We introduce two approximation error bounds based on the Dobrushin's comparison theorem and apply our bounds to derive a greedy expansion algorithm that efficiently guides the selection of neighbor nodes for localized inference. We verify our theoretical bounds on various datasets and demonstrate that our localized inference algorithm can provide fast and accurate approximation for large graphical models.

Reliability on cloud providers for ASR inference to support child-centered voice-based applications is becoming challenging due to regulatory and privacy challenges. Motivated by a privacy-preserving design, this study aims to develop a lightweight & efficient Whisper ASR system capable of running on a Raspberry Pi. Upon evaluation of the MyST corpus and by examining various filtering strategies to fine-tune the `tiny.en' model, a Word Error Rate (WER) of 15.9% was achieved (11.8% filtered). A low-rank compression reduces the encoder size by 0.51M with 1.26x faster inference in GPU, with 11% relative WER increase. During inference on Pi, the compressed version required ~2 GFLOPS fewer computations. The RTF for both the models ranged between [0.23-0.41] for various input audio durations. Analyzing the RAM usage and CPU temperature showed that the PI was capable of handling both the tiny models, however it was noticed that small models initiated additional overhead/thermal throttling.

This paper presents a configurable Convolutional Neural Network Accelerator (CNNA) for a System on Chip design (SoC). The goal was to accelerate inference of different deep learning networks on an embedded SoC platform. The presented CNNA has a scalable architecture which uses High Level Synthesis (HLS) and SystemC for the hardware accelerator. It is able to accelerate any Convolutional Neural Network (CNN) exported from Python and supports a combination of convolutional, max-pooling, and fully connected layers. A training method with fixed-point quantized weights is proposed and presented in the paper. The CNNA is template-based, enabling it to scale for different targets of the Xilinx Zynq platform. This approach enables design space exploration, which makes it possible to explore several configurations of the CNNA during C- and RTL-simulation, fitting it to the desired platform and model. The CNN VGG16 was used to test the solution on a Xilinx Ultra96 board using PYNQ. The result gave a high level of accuracy in training with an auto-scaled fixed-point Q2.14 format compared to a similar floating-point model. It was able to perform inference in 2.0 seconds, while having an average power consumption of 2.63 W, which corresponds to a power efficiency of 6.0 GOPS/W.

Recent advancements in large language models (LLMs) have shifted focus toward scaling inference-time compute, improving performance without retraining the model. A common approach is to sample multiple outputs in parallel, and select one of these as the final output. However, work to date has focused on English and a handful of domains such as math and code. In contrast, we are most interested in techniques that generalize across open-ended tasks, formally verifiable tasks, and across languages. In this work, we study how to robustly scale inference-time compute for open-ended generative tasks in a multilingual, multi-task setting. Our findings show that both sampling strategy based on temperature variation and selection strategy must be adapted to account for diverse domains and varied language settings. We evaluate existing selection methods, revealing that strategies effective in English often fail to generalize across languages. We propose novel sampling and selection strategies specifically adapted for multilingual and multi-task inference scenarios, and show they yield notable gains across languages and tasks. In particular, our combined sampling and selection methods lead to an average +6.8 jump in win-rates for our 8B models on m-ArenaHard-v2.0 prompts, against proprietary models such as Gemini. At larger scale, Command-A (111B model) equipped with our methods, shows +9.0 improvement in win-rates on the same benchmark with just five samples against single-sample decoding, a substantial increase at minimal cost. Our results underscore the need for language- and task-aware approaches to inference-time compute, aiming to democratize performance improvements in underrepresented languages.

We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful deliberation during problem solving, achieving outstanding performance across multiple benchmarks. Although there are already many excellent works related to inference models in the current community, there are still many problems with reproducing high-performance inference models due to incomplete disclosure of training details. This report provides an in-depth analysis of the reasoning model, covering the entire post-training workflow from data preparation and long Chain-of-Thought supervised fine-tuning (long CoT SFT) to reinforcement learning (RL), along with detailed ablation studies for each experimental component. For SFT data, our experiments show that a small number of high-quality data sources are more effective than a large number of diverse data sources, and that difficult samples can achieve better results without accuracy filtering. In addition, we investigate two key issues with current clipping mechanisms in RL: Clipping suppresses critical exploration signals and ignores suboptimal trajectories. To address these challenges, we propose Gradient-Preserving clipping Policy Optimization (GPPO) that gently backpropagates gradients from clipped tokens. GPPO not only enhances the model's exploration capacity but also improves its efficiency in learning from negative samples. Klear-Reasoner exhibits exceptional reasoning abilities in mathematics and programming, scoring 90.5\% on AIME 2024, 83.2\% on AIME 2025, 66.0\% on LiveCodeBench V5 and 58.1\% on LiveCodeBench V6.

Recently, large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws, which significantly increase model size. However, the huge computation overhead during inference hinders the deployment in industrial applications. Many works leverage traditional compression approaches to boost model inference, but these always introduce additional training costs to restore the performance and the pruning results typically show noticeable performance drops compared to the original model when aiming for a specific level of acceleration. To address these issues, we propose a fine-grained token-wise pruning approach for the LLMs, which presents a learnable router to adaptively identify the less important tokens and skip them across model blocks to reduce computational cost during inference. To construct the router efficiently, we present a search-based sparsity scheduler for pruning sparsity allocation, a trainable router combined with our proposed four low-dimensional factors as input and three proposed losses. We conduct extensive experiments across different benchmarks on different LLMs to demonstrate the superiority of our method. Our approach achieves state-of-the-art (SOTA) pruning results, surpassing other existing pruning methods. For instance, our method outperforms BlockPruner and ShortGPT by approximately 10 points on both LLaMA2-7B and Qwen1.5-7B in accuracy retention at comparable token sparsity levels.

Large Reasoning Models (LRMs) have demonstrated remarkable performance on tasks such as mathematics and code generation. Motivated by these strengths, recent work has empirically demonstrated the effectiveness of LRMs as guard models in improving harmful query detection. However, LRMs typically generate long reasoning traces during inference, causing substantial computational overhead. In this paper, we introduce PSRT, a method that replaces the model's reasoning process with a Prefilled Safe Reasoning Trace, thereby significantly reducing the inference cost of LRMs. Concretely, PSRT prefills "safe reasoning virtual tokens" from a constructed dataset and learns over their continuous embeddings. With the aid of indicator tokens, PSRT enables harmful-query detection in a single forward pass while preserving the classification effectiveness of LRMs. We evaluate PSRT on 7 models, 13 datasets, and 8 jailbreak methods. In terms of efficiency, PSRT completely removes the overhead of generating reasoning tokens during inference. In terms of classification performance, PSRT achieves nearly identical accuracy, with only a minor average F1 drop of 0.015 across 7 models and 5 datasets.

One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during inference. This survey focuses on these inference-time approaches. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms, and efficient generation. Token-level generation algorithms, often called decoding algorithms, operate by sampling a single token at a time or constructing a token-level search space and then selecting an output. These methods typically assume access to a language model's logits, next-token distributions, or probability scores. Meta-generation algorithms work on partial or full sequences, incorporating domain knowledge, enabling backtracking, and integrating external information. Efficient generation methods aim to reduce token costs and improve the speed of generation. Our survey unifies perspectives from three research communities: traditional natural language processing, modern LLMs, and machine learning systems.

Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in complex task-solving. However, their deliberative reasoning process leads to inefficiencies in token usage, memory consumption, and inference time. Thus, this survey provides a review of efficient inference methods designed specifically for LRMs, focusing on mitigating token inefficiency while preserving the reasoning quality. First, we introduce a taxonomy to group the recent methods into two main categories: (a) explicit compact Chain-of-Thought (CoT), which reduces tokens while keeping the explicit reasoning structure, and (b) implicit latent CoT, which encodes reasoning steps within hidden representations instead of explicit tokens. Meanwhile, we discuss their strengths and weaknesses. Then, we conduct empirical analyses on existing methods from performance and efficiency aspects. Besides, we present open challenges in this field, including human-centric controllable reasoning, trade-off between interpretability and efficiency of reasoning, ensuring safety of efficient reasoning, and broader applications of efficient reasoning. In addition, we highlight key insights for enhancing LRMs' inference efficiency via techniques such as model merging, new architectures, and agent routers. We hope this work serves as a valuable guide, helping researchers overcome challenges in this vibrant fieldhttps://github.com/yueliu1999/Awesome-Efficient-Inference-for-LRMs.

Exploiting sparsity underlying neural networks has become one of the most potential methodologies to reduce the memory footprint, I/O cost, and computation workloads during inference. And the degree of sparsity one can exploit has become higher as larger model sizes have been considered along with the trend of pre-training giant models. On the other hand, compared with quantization that has been a widely supported option, acceleration through high-degree sparsity is not supported in most computing platforms. In this work, we introduce the first commercial hardware platform supporting high-degree sparsity acceleration up to 32 times -- S4. Combined with state-of-the-art sparse pruning techniques, we demonstrate several-times practical inference speedup on S4 over mainstream inference platforms such as Nvidia T4. We also show that in practice a sparse model of larger size can achieve both higher accuracy and higher throughput on S4 than a dense model of smaller size.

Large Language Models (LLMs) with billions of parameters have drastically transformed AI applications. However, their demanding computation during inference has raised significant challenges for deployment on resource-constrained devices. Despite recent trends favoring alternative activation functions such as GELU or SiLU, known for increased computation, this study strongly advocates for reinstating ReLU activation in LLMs. We demonstrate that using the ReLU activation function has a negligible impact on convergence and performance while significantly reducing computation and weight transfer. This reduction is particularly valuable during the memory-bound inference step, where efficiency is paramount. Exploring sparsity patterns in ReLU-based LLMs, we unveil the reutilization of activated neurons for generating new tokens and leveraging these insights, we propose practical strategies to substantially reduce LLM inference computation up to three times, using ReLU activations with minimal performance trade-offs.

While neural networks have advanced the frontiers in many applications, they often come at a high computational cost. Reducing the power and latency of neural network inference is key if we want to integrate modern networks into edge devices with strict power and compute requirements. Neural network quantization is one of the most effective ways of achieving these savings but the additional noise it induces can lead to accuracy degradation. In this white paper, we introduce state-of-the-art algorithms for mitigating the impact of quantization noise on the network's performance while maintaining low-bit weights and activations. We start with a hardware motivated introduction to quantization and then consider two main classes of algorithms: Post-Training Quantization (PTQ) and Quantization-Aware-Training (QAT). PTQ requires no re-training or labelled data and is thus a lightweight push-button approach to quantization. In most cases, PTQ is sufficient for achieving 8-bit quantization with close to floating-point accuracy. QAT requires fine-tuning and access to labeled training data but enables lower bit quantization with competitive results. For both solutions, we provide tested pipelines based on existing literature and extensive experimentation that lead to state-of-the-art performance for common deep learning models and tasks.

Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we decompose the inference process into the encoding, denoising, and decoding stages, and observe that cache-based acceleration methods often lead to substantial memory surges in the latter two stages. To address this problem, we analyze the characteristics of inference across different stages and propose stage-specific strategies for reducing memory consumption: 1) Asynchronous Cache Swapping. 2) Feature chunk. 3) Slicing latents to decode. At the same time, we ensure that the time overhead introduced by these three strategies remains lower than the acceleration gains themselves. Compared with the baseline, our approach achieves faster inference speed and lower memory usage, while maintaining quality degradation within an acceptable range. The Code is available at https://github.com/NKUShaw/LightCache .

The simultaneous rise of machine learning as a service and concerns over user privacy have increasingly motivated the need for private inference (PI). While recent work demonstrates PI is possible using cryptographic primitives, the computational overheads render it impractical. The community is largely unprepared to address these overheads, as the source of slowdown in PI stems from the ReLU operator whereas optimizations for plaintext inference focus on optimizing FLOPs. In this paper we re-think the ReLU computation and propose optimizations for PI tailored to properties of neural networks. Specifically, we reformulate ReLU as an approximate sign test and introduce a novel truncation method for the sign test that significantly reduces the cost per ReLU. These optimizations result in a specific type of stochastic ReLU. The key observation is that the stochastic fault behavior is well suited for the fault-tolerant properties of neural network inference. Thus, we provide significant savings without impacting accuracy. We collectively call the optimizations Circa and demonstrate improvements of up to 4.7x storage and 3x runtime over baseline implementations; we further show that Circa can be used on top of recent PI optimizations to obtain 1.8x additional speedup.

Generative models have made significant impacts across various domains, largely due to their ability to scale during training by increasing data, computational resources, and model size, a phenomenon characterized by the scaling laws. Recent research has begun to explore inference-time scaling behavior in Large Language Models (LLMs), revealing how performance can further improve with additional computation during inference. Unlike LLMs, diffusion models inherently possess the flexibility to adjust inference-time computation via the number of denoising steps, although the performance gains typically flatten after a few dozen. In this work, we explore the inference-time scaling behavior of diffusion models beyond increasing denoising steps and investigate how the generation performance can further improve with increased computation. Specifically, we consider a search problem aimed at identifying better noises for the diffusion sampling process. We structure the design space along two axes: the verifiers used to provide feedback, and the algorithms used to find better noise candidates. Through extensive experiments on class-conditioned and text-conditioned image generation benchmarks, our findings reveal that increasing inference-time compute leads to substantial improvements in the quality of samples generated by diffusion models, and with the complicated nature of images, combinations of the components in the framework can be specifically chosen to conform with different application scenario.

Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents Transformer models from being used in production. To address this gap, model compression techniques such as quantization and pruning may be used to improve inference efficiency. However, these compression techniques require specialized software to apply and deploy at scale. In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators. We demonstrate the efficiency of our pipeline by creating a Fast DistilBERT model showing minimal accuracy loss on the question-answering SQuADv1.1 benchmark, and throughput results under typical production constraints and environments. Our results outperform existing state-of-the-art Neural Magic's DeepSparse runtime performance by up to 50% and up to 4.1x performance speedup over ONNX Runtime. Source code is publicly available at https://github.com/intel/intel-extension-for-transformers.

Recently, large-scale transformer-based models have been proven to be effective over various tasks across many domains. Nevertheless, applying them in industrial production requires tedious and heavy works to reduce inference costs. To fill such a gap, we introduce a scalable inference solution: Easy and Efficient Transformer (EET), including a series of transformer inference optimization at the algorithm and implementation levels. First, we design highly optimized kernels for long inputs and large hidden sizes. Second, we propose a flexible CUDA memory manager to reduce the memory footprint when deploying a large model. Compared with the state-of-the-art transformer inference library (Faster Transformer v4.0), EET can achieve an average of 1.40-4.20x speedup on the transformer decoder layer with an A100 GPU

Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. In this paper, we study the scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods. Moreover, current work largely provides negative results for a number of these strategies. In this work, we analyze two primary mechanisms to scale test-time computation: (1) searching against dense, process-based verifier reward models; and (2) updating the model's distribution over a response adaptively, given the prompt at test time. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt. This observation motivates applying a "compute-optimal" scaling strategy, which acts to most effectively allocate test-time compute adaptively per prompt. Using this compute-optimal strategy, we can improve the efficiency of test-time compute scaling by more than 4x compared to a best-of-N baseline. Additionally, in a FLOPs-matched evaluation, we find that on problems where a smaller base model attains somewhat non-trivial success rates, test-time compute can be used to outperform a 14x larger model.

Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting memory reduction and inference acceleration, which underscore the redundancy in LLMs. However, most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures. Besides, traditional architecture search methods, limited by the elevated complexity with extensive parameters, struggle to demonstrate their effectiveness on LLMs. In this paper, we propose a training-free architecture search framework to identify optimal subnets that preserve the fundamental strengths of the original LLMs while achieving inference acceleration. Furthermore, after generating subnets that inherit specific weights from the original LLMs, we introduce a reformation algorithm that utilizes the omitted weights to rectify the inherited weights with a small amount of calibration data. Compared with SOTA training-free structured pruning works that can generate smaller networks, our method demonstrates superior performance across standard benchmarks. Furthermore, our generated subnets can directly reduce the usage of GPU memory and achieve inference acceleration.

Despite their remarkable success in complex tasks propelling widespread adoption, large language-model-based agents still face critical deployment challenges due to prohibitive latency and inference costs. While recent work has explored various methods to accelerate inference, existing approaches suffer from significant limitations: they either fail to preserve performance fidelity, require extensive offline training of router modules, or incur excessive operational costs. Moreover, they provide minimal user control over the tradeoff between acceleration and other performance metrics. To address these gaps, we introduce Dynamic Speculative Planning (DSP), an asynchronous online reinforcement learning framework that provides lossless acceleration with substantially reduced costs without requiring additional pre-deployment preparation. DSP explicitly optimizes a joint objective balancing end-to-end latency against dollar cost, allowing practitioners to adjust a single parameter that steers the system toward faster responses, cheaper operation, or any point along this continuum. Experiments on two standard agent benchmarks demonstrate that DSP achieves comparable efficiency to the fastest lossless acceleration method while reducing total cost by 30% and unnecessary cost up to 60%. Our code and data are available through https://github.com/guanyilin428/Dynamic-Speculative-Planning.

Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typically, the number of activated experts presents a trade-off: fewer experts reduce computational costs, while more experts improve performance. Recent studies reveal that not all activated experts contribute equally to model performance, with some providing minimal utility, particularly when finetuning pretrained MoE models for specialized downstream tasks. The co-existence of significant and redundant parameters in experts provides us an opportunity to reduce the number of activated experts while maintaining model performance. In this work, we propose the concept of compressed experts, lightweight modules that serve as compact representations of full experts. Our approach preserves the most important experts while replacing other auxiliary activated experts with compressed experts. The reduction of active parameters significantly lowers inference costs while achieving comparable performance. Extensive experiments on models including Phi-MoE and OLMoE demonstrate that compressed experts recover over 90% of full expert performance across various tasks while reducing more than 30% active parameters and saving 20% in inference costs. This approach enables efficient deployment of MoE models in resource-constrained settings and facilitates scaling to larger models with manageable overhead. Our code is available at https://github.com/yifei-he/Compressed-Experts.

Chain-of-Thought significantly enhances a model's reasoning capability, but it also comes with a considerable increase in inference costs due to long chains. With the observation that the reasoning path can be easily compressed under easy tasks but struggle on hard tasks, we explore the feasibility of elastically controlling the length of reasoning paths with only one model, thereby reducing the inference overhead of reasoning models dynamically based on task difficulty. We introduce a new tuning and inference strategy named CoT-Valve, designed to allow models to generate reasoning chains of varying lengths. To achieve this, we propose to identify a direction in the parameter space that, when manipulated, can effectively control the length of generated CoT. Moreover, we show that this property is valuable for compressing the reasoning chain. We construct datasets with chains from long to short for the same questions and explore two enhanced strategies for CoT-Valve: (1) a precise length-compressible CoT tuning method, and (2) a progressive chain length compression approach. Our experiments show that CoT-Valve successfully enables controllability and compressibility of the chain and shows better performance than the prompt-based control. We applied this method to QwQ-32B-Preview, reducing reasoning chains on GSM8K from 741 to 225 tokens with a minor performance drop (95.07% to 94.92%) and on AIME from 6827 to 4629 tokens, with only one additional incorrect answer.

In this paper, we present a novel method that reduces model inference latency during distributed deployment of Large Language Models (LLMs). Our contribution is an optimized inference deployment scheme that address the current limitations of state-of-the-art quantization kernels when used in conjunction with Tensor Parallel (TP). Our method preserves data locality in GPU memory access patterns and exploits a priori knowledge of TP to reduce global communication. We demonstrate an up to 1.81x speedup over existing methods for Llama-70B and up to 1.78x speedup for IBM WatsonX's Granite-20B MLP layer problem sizes on A100 and H100 NVIDIA DGX Systems for a variety of TP settings.

Large language models have been widely adopted across different tasks, but their auto-regressive generation nature often leads to inefficient resource utilization during inference. While batching is commonly used to increase throughput, performance gains plateau beyond a certain batch size, especially with smaller models, a phenomenon that existing literature typically explains as a shift to the compute-bound regime. In this paper, through an in-depth GPU-level analysis, we reveal that large-batch inference remains memory-bound, with most GPU compute capabilities underutilized due to DRAM bandwidth saturation as the primary bottleneck. To address this, we propose a Batching Configuration Advisor (BCA) that optimizes memory allocation, reducing GPU memory requirements with minimal impact on throughput. The freed memory and underutilized GPU compute capabilities can then be leveraged by concurrent workloads. Specifically, we use model replication to improve serving throughput and GPU utilization. Our findings challenge conventional assumptions about LLM inference, offering new insights and practical strategies for improving resource utilization, particularly for smaller language models.

The recent rise of privacy concerns has led researchers to devise methods for private neural inference -- where inferences are made directly on encrypted data, never seeing inputs. The primary challenge facing private inference is that computing on encrypted data levies an impractically-high latency penalty, stemming mostly from non-linear operators like ReLU. Enabling practical and private inference requires new optimization methods that minimize network ReLU counts while preserving accuracy. This paper proposes DeepReDuce: a set of optimizations for the judicious removal of ReLUs to reduce private inference latency. The key insight is that not all ReLUs contribute equally to accuracy. We leverage this insight to drop, or remove, ReLUs from classic networks to significantly reduce inference latency and maintain high accuracy. Given a target network, DeepReDuce outputs a Pareto frontier of networks that tradeoff the number of ReLUs and accuracy. Compared to the state-of-the-art for private inference DeepReDuce improves accuracy and reduces ReLU count by up to 3.5% (iso-ReLU count) and 3.5times (iso-accuracy), respectively.

The growing demand for efficient Large Language Model (LLM) inference requires a holistic optimization on algorithms, systems, and hardware. However, very few works have fundamentally changed the generation pattern: each token needs one forward pass and one KV cache. This can be sub-optimal because we found that LLMs are extremely capable of self-identifying the exact dose of information that a single KV cache can store, and many tokens can be generated confidently without global context. Based on this insight, we introduce HAMburger, a Hierarchically Auto-regressive Model that redefines resource allocation in LLMs by moving beyond uniform computation and storage per token during inference. Stacking a compositional embedder and a micro-step decoder in between a base LLM, HAMburger smashes multiple tokens into a single KV and generates several tokens per step. Additionally, HAMburger functions as a speculative decoding framework where it can blindly trust self-drafted tokens. As a result, HAMburger shifts the growth of KV cache and forward FLOPs from linear to sub-linear with respect to output length, and adjusts its inference speed based on query perplexity and output structure. Extensive evaluations show that HAMburger reduces the KV cache computation by up to 2times and achieves up to 2times TPS, while maintaining quality in both short- and long-context tasks. Our method explores an extremely challenging inference regime that requires both computation- and memory-efficiency with a hardware-agnostic design.

We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering tradeoffs for inference for large Transformer-based models is important as use cases of these models are growing rapidly throughout application areas. We develop a simple analytical model for inference efficiency to select the best multi-dimensional partitioning techniques optimized for TPU v4 slices based on the application requirements. We combine these with a suite of low-level optimizations to achieve a new Pareto frontier on the latency and model FLOPS utilization (MFU) tradeoffs on 500B+ parameter models that outperforms the FasterTransformer suite of benchmarks. We further show that with appropriate partitioning, the lower memory requirements of multiquery attention (i.e. multiple query heads share single key/value head) enables scaling up to 32x larger context lengths. Finally, we achieve a low-batch-size latency of 29ms per token during generation (using int8 weight quantization) and a 76% MFU during large-batch-size processing of input tokens, while supporting a long 2048-token context length on the PaLM 540B parameter model.

Scaling test-time compute has emerged as a key strategy for enhancing the reasoning capabilities of large language models (LLMs), particularly in tasks like mathematical problem-solving. A traditional approach, Self-Consistency (SC), generates multiple solutions to a problem and selects the most common answer via majority voting. Another common method involves scoring each solution with a reward model (verifier) and choosing the best one. Recent advancements in Generative Reward Models (GenRM) reframe verification as a next-token prediction task, enabling inference-time scaling along a new axis. Specifically, GenRM generates multiple verification chains-of-thought to score each solution. Under a limited inference budget, this introduces a fundamental trade-off: should you spend the budget on scaling solutions via SC or generate fewer solutions and allocate compute to verification via GenRM? To address this, we evaluate GenRM against SC under a fixed inference budget. Interestingly, we find that SC is more compute-efficient than GenRM for most practical inference budgets across diverse models and datasets. For instance, GenRM first matches SC after consuming up to 8x the inference compute and requires significantly more compute to outperform it. Furthermore, we derive inference scaling laws for the GenRM paradigm, revealing that compute-optimal inference favors scaling solution generation more aggressively than scaling the number of verifications. Our work provides practical guidance on optimizing test-time scaling by balancing solution generation and verification. The code is available at https://github.com/nishadsinghi/sc-genrm-scaling.

The introduction of ChatGPT has led to a significant increase in the utilization of Large Language Models (LLMs) for addressing downstream tasks. There's an increasing focus on cost-efficient training and deployment within this context. Low-cost training and deployment of LLMs represent the future development trend. This paper reviews the evolution of large language model training techniques and inference deployment technologies aligned with this emerging trend. The discussion on training includes various aspects, including data preprocessing, training architecture, pre-training tasks, parallel training, and relevant content related to model fine-tuning. On the inference side, the paper covers topics such as model compression, parallel computation, memory scheduling, and structural optimization. It also explores LLMs' utilization and provides insights into their future development.

Large Language Models (LLMs) are increasingly relied upon for solving complex reasoning tasks in domains such as mathematics, logic, and multi-step question answering. A growing line of work seeks to improve reasoning quality by scaling inference time compute particularly through Process Reward Models (PRMs), used to reward the reasoning at intermediate steps. While effective, these methods introduce substantial computational overhead, especially when generating large numbers of solutions in parallel. In this paper, we investigate whether PRMs can be used mid-generation to provide early signals that enable the rejection of suboptimal candidates before full generation of step is complete. We introduce the hypothesis that PRMs are also Partial Reward Models, meaning that the scores they assign to partially completed reasoning step are predictive of final output quality. This allows for principled early rejection based on intermediate token-level signals. We support this hypothesis both theoretically, by proving that the risk of discarding optimal beams decreases exponentially with generation length and empirically, by demonstrating a strong correlation between partial and final rewards across multiple reward models. On math reasoning benchmarks, our method achieves up to 1.4times-9times reduction in inference FLOPs without degrading final performance. These results suggest that early rejection is a powerful mechanism for improving the compute-efficiency of reasoning in LLMs.

Large Reasoning Models (LRMs) perform strongly in complex reasoning tasks via Chain-of-Thought (CoT) prompting, but often suffer from verbose outputs caused by redundant content, increasing computational overhead, and degrading user experience. Existing compression methods either operate post-hoc pruning, risking disruption to reasoning coherence, or rely on sampling-based selection, which fails to intervene effectively during generation. In this work, we introduce a confidence-guided perspective to explain the emergence of redundant reflection in LRMs, identifying two key patterns: Confidence Deficit, where the model reconsiders correct steps due to low internal confidence, and Termination Delay, where reasoning continues even after reaching a confident answer. Based on this analysis, we propose ConCISE (Confidence-guided Compression In Step-by-step Efficient Reasoning), a framework that simplifies reasoning chains by reinforcing the model's confidence during inference, thus preventing the generation of redundant reflection steps. It integrates Confidence Injection to stabilize intermediate steps and Early Stopping to terminate reasoning when confidence is sufficient. Extensive experiments demonstrate that fine-tuning LRMs on ConCISE-generated data yields significantly shorter outputs, reducing length by up to approximately 50% under SimPO, while maintaining high task accuracy. ConCISE consistently outperforms existing baselines across multiple reasoning benchmarks.

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. Exploiting the heterogeneous capabilities of edge LLMs is crucial for diverse emerging applications, as it enables greater cost-effectiveness and reduced latency. In this work, we introduce Mixture-of-Edge-Experts (MoE^2), a novel collaborative inference framework for edge LLMs. We formulate the joint gating and expert selection problem to optimize inference performance under energy and latency constraints. Unlike conventional MoE problems, LLM expert selection is significantly more challenging due to the combinatorial nature and the heterogeneity of edge LLMs across various attributes. To this end, we propose a two-level expert selection mechanism through which we uncover an optimality-preserving property of gating parameters across expert selections. This property enables the decomposition of the training and selection processes, significantly reducing complexity. Furthermore, we leverage the objective's monotonicity and design a discrete monotonic optimization algorithm for optimal expert selection. We implement edge servers with NVIDIA Jetson AGX Orins and NVIDIA RTX 4090 GPUs, and perform extensive experiments. Our results validate that performance improvements of various LLM models and show that our MoE^2 method can achieve optimal trade-offs among different delay and energy budgets, and outperforms baselines under various system resource constraints.

The Large Language Model (LLM) is widely employed for tasks such as intelligent assistants, text summarization, translation, and multi-modality on mobile phones. However, the current methods for on-device LLM deployment maintain slow inference speed, which causes poor user experience. To facilitate high-efficiency LLM deployment on device GPUs, we propose four optimization techniques: (a) a symbolic expression-based approach to support dynamic shape model inference; (b) operator optimizations and execution priority setting to enhance inference speed and reduce phone lagging; (c) an FP4 quantization method termed M0E4 to reduce dequantization overhead; (d) a sub-tensor-based technique to eliminate the need for copying KV cache after LLM inference. Furthermore, we implement these methods in our mobile inference engine, Transformer-Lite, which is compatible with both Qualcomm and MTK processors. We evaluated Transformer-Lite's performance using LLMs with varied architectures and parameters ranging from 2B to 14B. Specifically, we achieved prefill and decoding speeds of 121 token/s and 14 token/s for ChatGLM2 6B, and 330 token/s and 30 token/s for smaller Gemma 2B, respectively. Compared with CPU-based FastLLM and GPU-based MLC-LLM, our engine attains over 10x speedup for the prefill speed and 2~3x speedup for the decoding speed.

Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference time, raising the natural question: when is the extra cost of deploying a larger model worth the anticipated boost in capabilities? Better understanding this tradeoff fundamentally could benefit from an inference efficiency metric that is both (i) easily comparable across models from different providers, and (ii) representative of the true cost of running queries in an isolated performance environment. Unfortunately, access to LLMs today is largely restricted to black-box text generation APIs and raw runtimes measured through this interface do not satisfy these desiderata: model providers can apply various software and hardware optimizations orthogonal to the model, and models served on shared infrastructure are susceptible to performance contention. To circumvent these problems, we propose a new metric for comparing inference efficiency across models. This metric puts models on equal footing as though they were served (i) on uniform hardware and software, and (ii) without performance contention. We call this metric the idealized runtime, and we propose a methodology to efficiently estimate this metric for autoregressive Transformer models. We also propose cost-aware variants that incorporate the number of accelerators needed to serve the model. Using these metrics, we compare ten state-of-the-art LLMs to provide the first analysis of inference efficiency-capability tradeoffs; we make several observations from this analysis, including the fact that the superior inference runtime performance of certain APIs is often a byproduct of optimizations within the API rather than the underlying model. Our methodology also facilitates the efficient comparison of different software and hardware stacks.

We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient estimator. Our results call into question common implicit assumptions that tighter ELBOs are better variational objectives for simultaneous model learning and inference amortization schemes. Based on our insights, we introduce three new algorithms: the partially importance weighted auto-encoder (PIWAE), the multiply importance weighted auto-encoder (MIWAE), and the combination importance weighted auto-encoder (CIWAE), each of which includes the standard importance weighted auto-encoder (IWAE) as a special case. We show that each can deliver improvements over IWAE, even when performance is measured by the IWAE target itself. Furthermore, our results suggest that PIWAE may be able to deliver simultaneous improvements in the training of both the inference and generative networks.

While frontier large language models (LLMs) continue to push capability boundaries, their deployment remains confined to GPU-powered cloud infrastructure. We challenge this paradigm with SmallThinker, a family of LLMs natively designed - not adapted - for the unique constraints of local devices: weak computational power, limited memory, and slow storage. Unlike traditional approaches that mainly compress existing models built for clouds, we architect SmallThinker from the ground up to thrive within these limitations. Our innovation lies in a deployment-aware architecture that transforms constraints into design principles. First, We introduce a two-level sparse structure combining fine-grained Mixture-of-Experts (MoE) with sparse feed-forward networks, drastically reducing computational demands without sacrificing model capacity. Second, to conquer the I/O bottleneck of slow storage, we design a pre-attention router that enables our co-designed inference engine to prefetch expert parameters from storage while computing attention, effectively hiding storage latency that would otherwise cripple on-device inference. Third, for memory efficiency, we utilize NoPE-RoPE hybrid sparse attention mechanism to slash KV cache requirements. We release SmallThinker-4B-A0.6B and SmallThinker-21B-A3B, which achieve state-of-the-art performance scores and even outperform larger LLMs. Remarkably, our co-designed system mostly eliminates the need for expensive GPU hardware: with Q4_0 quantization, both models exceed 20 tokens/s on ordinary consumer CPUs, while consuming only 1GB and 8GB of memory respectively. SmallThinker is publicly available at hf.co/PowerInfer/SmallThinker-4BA0.6B-Instruct and hf.co/PowerInfer/SmallThinker-21BA3B-Instruct.

Matrix multiplication (MatMul) typically dominates the overall computational cost of large language models (LLMs). This cost only grows as LLMs scale to larger embedding dimensions and context lengths. In this work, we show that MatMul operations can be completely eliminated from LLMs while maintaining strong performance at billion-parameter scales. Our experiments show that our proposed MatMul-free models achieve performance on-par with state-of-the-art Transformers that require far more memory during inference at a scale up to at least 2.7B parameters. We investigate the scaling laws and find that the performance gap between our MatMul-free models and full precision Transformers narrows as the model size increases. We also provide a GPU-efficient implementation of this model which reduces memory usage by up to 61% over an unoptimized baseline during training. By utilizing an optimized kernel during inference, our model's memory consumption can be reduced by more than 10x compared to unoptimized models. To properly quantify the efficiency of our architecture, we build a custom hardware solution on an FPGA which exploits lightweight operations beyond what GPUs are capable of. We processed billion-parameter scale models at 13W beyond human readable throughput, moving LLMs closer to brain-like efficiency. This work not only shows how far LLMs can be stripped back while still performing effectively, but also points at the types of operations future accelerators should be optimized for in processing the next generation of lightweight LLMs. Our code implementation is available at https://github.com/ridgerchu/matmulfreellm.

We introduce stochastic activations. This novel strategy randomly selects between several non-linear functions in the feed-forward layer of a large language model. In particular, we choose between SILU or RELU depending on a Bernoulli draw. This strategy circumvents the optimization problem associated with RELU, namely, the constant shape for negative inputs that prevents the gradient flow. We leverage this strategy in two ways: (1) We use stochastic activations during pre-training and fine-tune the model with RELU, which is used at inference time to provide sparse latent vectors. This reduces the inference FLOPs and translates into a significant speedup in the CPU. Interestingly, this leads to much better results than training from scratch with the RELU activation function. (2) We evaluate stochastic activations for generation. This strategy performs reasonably well: it is only slightly inferior to the best deterministic non-linearity, namely SILU combined with temperature scaling. This offers an alternative to existing strategies by providing a controlled way to increase the diversity of the generated text.

Techniques that enhance inference through increased computation at test-time have recently gained attention. In this survey, we investigate the current state of LLM Inference-Time Self-Improvement from three different perspectives: Independent Self-improvement, focusing on enhancements via decoding or sampling methods; Context-Aware Self-Improvement, leveraging additional context or datastore; and Model-Aided Self-Improvement, achieving improvement through model collaboration. We provide a comprehensive review of recent relevant studies, contribute an in-depth taxonomy, and discuss challenges and limitations, offering insights for future research.

Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks. However, the inference process for LLMs comes with significant computational costs. In this paper, we propose an efficient LLM inference pipeline that harnesses the power of LLMs. Our approach begins by tapping into the potential of LLMs to accurately perceive and predict the response length with minimal overhead. By leveraging this information, we introduce an efficient sequence scheduling technique that groups queries with similar response lengths into micro-batches. We evaluate our approach on real-world instruction datasets using the LLaMA-based model, and our results demonstrate an impressive 86% improvement in inference throughput without compromising effectiveness. Notably, our method is orthogonal to other inference acceleration techniques, making it a valuable addition to many existing toolkits (e.g., FlashAttention, Quantization) for LLM inference.

Recently, long-thought reasoning LLMs, such as OpenAI's O1, adopt extended reasoning processes similar to how humans ponder over complex problems. This reasoning paradigm significantly enhances the model's problem-solving abilities and has achieved promising results. However, long-thought reasoning process leads to a substantial increase in inference time. A pressing challenge is reducing the inference overhead of long-thought LLMs while ensuring accuracy. In this paper, we experimentally demonstrate that long-thought reasoning models struggle to effectively allocate token budgets based on problem difficulty and reasoning redundancies. To address this, we propose Length-Harmonizing Fine-Tuning (O1-Pruner), aiming at minimizing reasoning overhead while maintaining accuracy. This effective fine-tuning method first estimates the LLM's baseline performance through pre-sampling and then uses RL-style fine-tuning to encourage the model to generate shorter reasoning processes under accuracy constraints. This allows the model to achieve efficient reasoning with lower redundancy while maintaining accuracy. Experiments on various mathematical reasoning benchmarks show that O1-Pruner not only significantly reduces inference overhead but also achieves higher accuracy, providing a novel and promising solution to this challenge. Our code is coming soon at https://github.com/StarDewXXX/O1-Pruner

Although Large Vision-Language Models (LVLMs) have achieved impressive results, their high computational cost poses a significant barrier to wider application. To enhance inference efficiency, most existing approaches depend on parameter-dependent or token-dependent strategies to reduce computational demands. However, these methods typically require complex training processes and struggle to consistently select the most relevant tokens. In this paper, we systematically analyze the above challenges and provide a series of valuable insights for inference acceleration. Based on these findings, we propose a novel framework, the Pruning All-Rounder (PAR). Different from previous works, PAR develops a meta-router to adaptively organize pruning flows across both tokens and layers. With a self-supervised learning manner, our method achieves a superior balance between performance and efficiency. Notably, PAR is highly flexible, offering multiple pruning versions to address a range of pruning scenarios. The code for this work will be made publicly available.

With the ubiquitous use of modern large language models (LLMs) across industries, the inference serving for these models is ever expanding. Given the high compute and memory requirements of modern LLMs, more and more top-of-the-line GPUs are being deployed to serve these models. Energy availability has come to the forefront as the biggest challenge for data center expansion to serve these models. In this paper, we present the trade-offs brought up by making energy efficiency the primary goal of LLM serving under performance SLOs. We show that depending on the inputs, the model, and the service-level agreements, there are several knobs available to the LLM inference provider to use for being energy efficient. We characterize the impact of these knobs on the latency, throughput, as well as the energy. By exploring these trade-offs, we offer valuable insights into optimizing energy usage without compromising on performance, thereby paving the way for sustainable and cost-effective LLM deployment in data center environments.

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their intensive computational and memory requirements present challenges, especially for devices with limited DRAM capacity. This paper tackles the challenge of efficiently running LLMs that exceed the available DRAM capacity by storing the model parameters on flash memory but bringing them on demand to DRAM. Our method involves constructing an inference cost model that harmonizes with the flash memory behavior, guiding us to optimize in two critical areas: reducing the volume of data transferred from flash and reading data in larger, more contiguous chunks. Within this flash memory-informed framework, we introduce two principal techniques. First, "windowing'" strategically reduces data transfer by reusing previously activated neurons, and second, "row-column bundling", tailored to the sequential data access strengths of flash memory, increases the size of data chunks read from flash memory. These methods collectively enable running models up to twice the size of the available DRAM, with a 4-5x and 20-25x increase in inference speed compared to naive loading approaches in CPU and GPU, respectively. Our integration of sparsity awareness, context-adaptive loading, and a hardware-oriented design paves the way for effective inference of LLMs on devices with limited memory.

Inference-time computation techniques, analogous to human System 2 Thinking, have recently become popular for improving model performances. However, most existing approaches suffer from several limitations: they are modality-specific (e.g., working only in text), problem-specific (e.g., verifiable domains like math and coding), or require additional supervision/training on top of unsupervised pretraining (e.g., verifiers or verifiable rewards). In this paper, we ask the question "Is it possible to generalize these System 2 Thinking approaches, and develop models that learn to think solely from unsupervised learning?" Interestingly, we find the answer is yes, by learning to explicitly verify the compatibility between inputs and candidate-predictions, and then re-framing prediction problems as optimization with respect to this verifier. Specifically, we train Energy-Based Transformers (EBTs) -- a new class of Energy-Based Models (EBMs) -- to assign an energy value to every input and candidate-prediction pair, enabling predictions through gradient descent-based energy minimization until convergence. Across both discrete (text) and continuous (visual) modalities, we find EBTs scale faster than the dominant Transformer++ approach during training, achieving an up to 35% higher scaling rate with respect to data, batch size, parameters, FLOPs, and depth. During inference, EBTs improve performance with System 2 Thinking by 29% more than the Transformer++ on language tasks, and EBTs outperform Diffusion Transformers on image denoising while using fewer forward passes. Further, we find that EBTs achieve better results than existing models on most downstream tasks given the same or worse pretraining performance, suggesting that EBTs generalize better than existing approaches. Consequently, EBTs are a promising new paradigm for scaling both the learning and thinking capabilities of models.

The demand for efficient processing of deep neural networks (DNNs) on embedded devices is a significant challenge limiting their deployment. Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference latency. It is known that unstructured sparsity results in lower accuracy degradation with respect to structured sparsity but the former needs extensive inference engine changes to get latency benefits. To tackle this challenge, we propose a solution to induce semi-structured activation sparsity exploitable through minor runtime modifications. To attain high speedup levels at inference time, we design a sparse training procedure with awareness of the final position of the activations while computing the General Matrix Multiplication (GEMM). We extensively evaluate the proposed solution across various models for image classification and object detection tasks. Remarkably, our approach yields a speed improvement of 1.25 times with a minimal accuracy drop of 1.1% for the ResNet18 model on the ImageNet dataset. Furthermore, when combined with a state-of-the-art structured pruning method, the resulting models provide a good latency-accuracy trade-off, outperforming models that solely employ structured pruning techniques.

The past several years have witnessed the success of transformer-based models, and their scale and application scenarios continue to grow aggressively. The current landscape of transformer models is increasingly diverse: the model size varies drastically with the largest being of hundred-billion parameters; the model characteristics differ due to the sparsity introduced by the Mixture-of-Experts; the target application scenarios can be latency-critical or throughput-oriented; the deployment hardware could be single- or multi-GPU systems with different types of memory and storage, etc. With such increasing diversity and the fast-evolving pace of transformer models, designing a highly performant and efficient inference system is extremely challenging. In this paper, we present DeepSpeed Inference, a comprehensive system solution for transformer model inference to address the above-mentioned challenges. DeepSpeed Inference consists of (1) a multi-GPU inference solution to minimize latency while maximizing the throughput of both dense and sparse transformer models when they fit in aggregate GPU memory, and (2) a heterogeneous inference solution that leverages CPU and NVMe memory in addition to the GPU memory and compute to enable high inference throughput with large models which do not fit in aggregate GPU memory. DeepSpeed Inference reduces latency by up to 7.3X over the state-of-the-art for latency-oriented scenarios and increases throughput by over 1.5x for throughput-oriented scenarios. Moreover, it enables trillion parameter scale inference under real-time latency constraints by leveraging hundreds of GPUs, an unprecedented scale for inference. It can inference 25x larger models than with GPU-only solutions, while delivering a high throughput of 84 TFLOPS (over 50% of A6000 peak).

Probabilistic circuits (PCs) are a tractable representation of probability distributions allowing for exact and efficient computation of likelihoods and marginals. There has been significant recent progress on improving the scale and expressiveness of PCs. However, PC training performance plateaus as model size increases. We discover that most capacity in existing large PC structures is wasted: fully-connected parameter layers are only sparsely used. We propose two operations: pruning and growing, that exploit the sparsity of PC structures. Specifically, the pruning operation removes unimportant sub-networks of the PC for model compression and comes with theoretical guarantees. The growing operation increases model capacity by increasing the size of the latent space. By alternatingly applying pruning and growing, we increase the capacity that is meaningfully used, allowing us to significantly scale up PC learning. Empirically, our learner achieves state-of-the-art likelihoods on MNIST-family image datasets and on Penn Tree Bank language data compared to other PC learners and less tractable deep generative models such as flow-based models and variational autoencoders (VAEs).

With increasing demands for efficiency, information retrieval has developed a branch of sparse retrieval, further advancing towards inference-free retrieval where the documents are encoded during indexing time and there is no model-inference for queries. Existing sparse retrieval models rely on FLOPS regularization for sparsification, while this mechanism was originally designed for Siamese encoders, it is considered to be suboptimal in inference-free scenarios which is asymmetric. Previous attempts to adapt FLOPS for inference-free scenarios have been limited to rule-based methods, leaving the potential of sparsification approaches for inference-free retrieval models largely unexplored. In this paper, we explore ell_0 inspired sparsification manner for inference-free retrievers. Through comprehensive out-of-domain evaluation on the BEIR benchmark, our method achieves state-of-the-art performance among inference-free sparse retrieval models and is comparable to leading Siamese sparse retrieval models. Furthermore, we provide insights into the trade-off between retrieval effectiveness and computational efficiency, demonstrating practical value for real-world applications.

Large Language Models (LLMs) have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scaling (TTS) improves reasoning quality, it often leads to overthinking, wasting tokens on redundant computations. This work investigates how to efficiently and adaptively guide LLM test-time scaling without additional training. Inspired by the concept of momentum in physics, we propose Momentum Uncertainty-guided Reasoning (MUR), which dynamically allocates thinking budgets to critical reasoning steps by tracking and aggregating stepwise uncertainty over time. To support flexible inference-time control, we introduce gamma-control, a simple mechanism that tunes the reasoning budget via a single hyperparameter. We provide in-depth theoretical proof to support the superiority of MUR in terms of stability and biases. MUR is comprehensively evaluated against various TTS methods across four challenging benchmarks (MATH-500, AIME24, AIME25, and GPQA-diamond) using different sizes of recent Qwen3 models (1.7B, 4B, and 8B). Results demonstrate that MUR reduces computation by over 50% on average while improving accuracy by 0.62-3.37%.

With the wide adoption of AI applications, there is a pressing need of enabling real-time neural network (NN) inference on small embedded devices, but deploying NNs and achieving high performance of NN inference on these small devices is challenging due to their extremely weak capabilities. Although NN partitioning and offloading can contribute to such deployment, they are incapable of minimizing the local costs at embedded devices. Instead, we suggest to address this challenge via agile NN offloading, which migrates the required computations in NN offloading from online inference to offline learning. In this paper, we present AgileNN, a new NN offloading technique that achieves real-time NN inference on weak embedded devices by leveraging eXplainable AI techniques, so as to explicitly enforce feature sparsity during the training phase and minimize the online computation and communication costs. Experiment results show that AgileNN's inference latency is >6x lower than the existing schemes, ensuring that sensory data on embedded devices can be timely consumed. It also reduces the local device's resource consumption by >8x, without impairing the inference accuracy.

Large language models (LLMs) are typically prompted to follow a single instruction per inference call. In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as Multi-Task Inference. For this purpose, we introduce the MTI Bench(Multi-Task Inference Benchmark), a comprehensive evaluation benchmark encompassing 5,000 instances across 25 tasks. Each task in the MTI Bench involves 2 to 3 sub-tasks. As expected, we first demonstrate that Multi-Task Inference reduces the total inference time by 1.46 times in average since it does not require multiple inference calls. Interestingly, contrary to the expectation that LLMs would perform better when tasks are divided, we find that state-of-the-art LLMs, such as Llama-2-Chat-70B and GPT-4, show up to 7.3% and 12.4% improved performance with Multi-Task Inference compared to Single-Task Inference on the MTI Bench. We release the MTI Bench dataset and our code at this link https://github.com/guijinSON/MTI-Bench.

Large Language Models (LLMs) are revolutionizing numerous industries, but their substantial computational demands create challenges for efficient deployment, particularly in cloud environments. Traditional approaches to inference serving often struggle with resource inefficiencies, leading to high operational costs, latency issues, and limited scalability. This article explores how Cloud Native technologies, such as containerization, microservices, and dynamic scheduling, can fundamentally improve LLM inference serving. By leveraging these technologies, we demonstrate how a Cloud Native system enables more efficient resource allocation, reduces latency, and enhances throughput in high-demand scenarios. Through real-world evaluations using Kubernetes-based autoscaling, we show that Cloud Native architectures can dynamically adapt to workload fluctuations, mitigating performance bottlenecks while optimizing LLM inference serving performance. This discussion provides a broader perspective on how Cloud Native frameworks could reshape the future of scalable LLM inference serving, offering key insights for researchers, practitioners, and industry leaders in cloud computing and artificial intelligence.

Recent studies have indicated that effectively utilizing inference-time compute is crucial for attaining better performance from large language models (LLMs). In this work, we propose a novel inference-aware fine-tuning paradigm, in which the model is fine-tuned in a manner that directly optimizes the performance of the inference-time strategy. We study this paradigm using the simple yet effective Best-of-N (BoN) inference strategy, in which a verifier selects the best out of a set of LLM-generated responses. We devise the first imitation learning and reinforcement learning~(RL) methods for BoN-aware fine-tuning, overcoming the challenging, non-differentiable argmax operator within BoN. We empirically demonstrate that our BoN-aware models implicitly learn a meta-strategy that interleaves best responses with more diverse responses that might be better suited to a test-time input -- a process reminiscent of the exploration-exploitation trade-off in RL. Our experiments demonstrate the effectiveness of BoN-aware fine-tuning in terms of improved performance and inference-time compute. In particular, we show that our methods improve the Bo32 performance of Gemma 2B on Hendrycks MATH from 26.8% to 30.8%, and pass@32 from 60.0% to 67.0%, as well as the pass@16 on HumanEval from 61.6% to 67.1%.

The deployment of large-scale models, such as large language models (LLMs) and sophisticated image generation systems, incurs substantial costs due to their computational demands. To mitigate these costs and address challenges related to scalability and data security, there is a growing shift towards decentralized systems for deploying such models. In these decentralized environments, efficient inference acceleration becomes crucial to manage computational resources effectively and enhance system responsiveness. In this work, we address the challenge of selecting optimal acceleration methods in decentralized systems by introducing a meta-learning-based framework. This framework automates the selection process by learning from historical performance data of various acceleration techniques across different tasks. Unlike traditional methods that rely on random selection or expert intuition, our approach systematically identifies the best acceleration strategies based on the specific characteristics of each task. We demonstrate that our meta-learning framework not only streamlines the decision-making process but also consistently outperforms conventional methods in terms of efficiency and performance. Our results highlight the potential of meta-learning to revolutionize inference acceleration in decentralized AI systems, offering a path towards more democratic and economically feasible artificial intelligence solutions.

The deployment of Large Language Models (LLMs) on edge devices is increasingly important to enhance on-device intelligence. Weight quantization is crucial for reducing the memory footprint of LLMs on devices. However, low-bit LLMs necessitate mixed precision matrix multiplication (mpGEMM) of low precision weights and high precision activations during inference. Existing systems, lacking native support for mpGEMM, resort to dequantize weights for high precision computation. Such an indirect way can lead to a significant inference overhead. In this paper, we introduce T-MAC, an innovative lookup table(LUT)-based method designed for efficient low-bit LLM (i.e., weight-quantized LLM) inference on CPUs. T-MAC directly supports mpGEMM without dequantization, while simultaneously eliminating multiplications and reducing additions required. Specifically, T-MAC transforms the traditional data-type-centric multiplication to bit-wise table lookup, and enables a unified and scalable mpGEMM solution. Our LUT-based kernels scale linearly to the weight bit-width. Evaluated on low-bit Llama and BitNet models, T-MAC demonstrates up to 4x increase in throughput and 70% reduction in energy consumption compared to llama.cpp. For BitNet-b1.58-3B, T-MAC delivers a token generation throughput of 30 tokens/s with a single core and 71 tokens/s with eight cores on M2-Ultra, and 11 tokens/s on lower-end devices like Raspberry Pi 5, which significantly exceeds the adult average reading speed. T-MAC with LUT-based computing paradigm, paves the way for the practical deployment of low-bit LLMs on resource-constrained edge devices without compromising computational efficiency. The system is open-sourced at https://github.com/microsoft/T-MAC.

In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential execution of computation and communication. This results in substantial underutilization of computing resources during the communication phase. To mitigate this inefficiency, various techniques have been developed to optimize the use of computational power throughout the communication process. These strategies primarily involve overlapping matrix computations and communications, as well as interleaving micro-batches across different requests. Nonetheless, these approaches either fall short of achieving ideal overlap or impose certain limitations on their application. To overcome these challenges, this paper introduces a novel strategy for computation-communication overlap that operates at the sequence level. This method not only enhances the degree of overlap but also minimizes the constraints on its applicability. Experimental evaluations conducted using 30b/70b models have demonstrated significant improvements in efficiency. Specifically, the proposed technique has been shown to reduce time consumption by approximately 35% on 4090 GPU and by roughly 15% on A800 GPU during the prefill stage of LLM inference.

Recently developed large language models (LLMs) such as ChatGPT, Claude, and Llama have demonstrated impressive abilities, and even surpass human-level performance in several tasks. Despite their success, the resource-intensive demands of these models, requiring significant computational power for both training and inference, limit their deployment to high-performance servers. Additionally, the extensive calculation requirements of the models often lead to increased latency in response times. With the increasing need for LLMs to operate efficiently on CPUs, research about lightweight models that are optimized for CPU inference has emerged. In this work, we introduce GEB-1.3B, a lightweight LLM trained on 550 billion tokens in both Chinese and English languages. We employ novel training techniques, including ROPE, Group-Query-Attention, and FlashAttention-2, to accelerate training while maintaining model performance. Additionally, we fine-tune the model using 10 million samples of instruction data to enhance alignment. GEB-1.3B exhibits outstanding performance on general benchmarks such as MMLU, C-Eval, and CMMLU, outperforming comparative models such as MindLLM-1.3B and TinyLLaMA-1.1B. Notably, the FP32 version of GEB-1.3B achieves commendable inference times on CPUs, with ongoing efforts to further enhance speed through advanced quantization techniques. The release of GEB-1.3B as an open-source model marks a significant contribution to the development of lightweight LLMs, promising to foster further research and innovation in the field.

The AIPC concept is gaining popularity, and more and more hybrid CPUs will be running AI models on client devices. However, the current AI inference framework overlooks the imbalanced hardware capability of hybrid CPUs, leading to low inference performance. To address this issue, we have introduced a dynamic parallel method for hybrid CPUs, which significantly increases LLM inference performance by balancing the workload for each core of a hybrid CPU before the parallel work starts. This method has enabled Neural Speed to achieve more than 90% (on average) of memory bandwidth on two hybrid Intel CPUs.

While Large Reasoning Models (LRMs) have demonstrated success in complex reasoning tasks through long chain-of-thought (CoT) reasoning, their inference often involves excessively verbose reasoning traces, resulting in substantial inefficiency. To address this, we propose Distilled Reasoning Pruning (DRP), a hybrid framework that combines inference-time pruning with tuning-based distillation, two widely used strategies for efficient reasoning. DRP uses a teacher model to perform skill-aware step decomposition and content pruning, and then distills the pruned reasoning paths into a student model, enabling it to reason both efficiently and accurately. Across several challenging mathematical reasoning datasets, we find that models trained with DRP achieve substantial improvements in token efficiency without sacrificing accuracy. Specifically, DRP reduces average token usage on GSM8K from 917 to 328 while improving accuracy from 91.7% to 94.1%, and achieves a 43% token reduction on AIME with no performance drop. Further analysis shows that aligning the reasoning structure of training CoTs with the student's reasoning capacity is critical for effective knowledge transfer and performance gains.

In recent years, the rapid advancement of large-scale pre-trained language models based on transformer architectures has revolutionized natural language processing tasks. Among these, ChatGPT has gained widespread popularity, demonstrating human-level conversational abilities and attracting over 100 million monthly users by late 2022. Concurrently, Baidu's commercial deployment of the Ernie Wenxin model has significantly enhanced marketing effectiveness through AI-driven technologies. This paper focuses on optimizing high-performance inference for Ernie models, emphasizing GPU acceleration and leveraging the Paddle inference framework. We employ techniques such as Faster Transformer for efficient model processing, embedding layer pruning to reduce computational overhead, and FP16 half-precision inference for enhanced computational efficiency. Additionally, our approach integrates efficient data handling strategies using multi-process parallel processing to minimize latency. Experimental results demonstrate that our optimized solution achieves up to an 8.96x improvement in inference speed compared to standard methods, while maintaining competitive performance.

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining the number of layers. Depth pruning, in contrast, removes entire layers or blocks, while keeping the size of the remaining weights unchanged. Most current research focuses on either width-only or a blend of width and depth pruning, with little comparative analysis between the two units (width vs. depth) concerning their impact on LLM inference efficiency. In this work, we show that a simple depth pruning approach can compete with recent width pruning methods in terms of zero-shot task performance. Our pruning method boosts inference speeds, especially under memory-constrained conditions that require limited batch sizes for running LLMs, where width pruning is ineffective. We hope this work can help deploy LLMs on local and edge devices.

We propose TETRIS, a novel method that optimizes the total throughput of batch speculative decoding in multi-request settings. Unlike existing methods that optimize for a single request or a group of requests as a whole, TETRIS actively selects the most promising draft tokens (for every request in a batch) to be accepted when verified in parallel, resulting in fewer rejected tokens and hence less wasted computing resources. Such an effective resource utilization to achieve fast inference in large language models (LLMs) is especially important to service providers with limited inference capacity. Compared to baseline speculative decoding, TETRIS yields a consistently higher acceptance rate and more effective utilization of the limited inference capacity. We show theoretically and empirically that TETRIS outperforms baseline speculative decoding and existing methods that dynamically select draft tokens, leading to a more efficient batch inference in LLMs.

Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading framework for on-device inference, addressing these issues with techniques like asynchronous prefetching, balanced memory locking, and flexible tensor preservation. These strategies enhance memory efficiency and mitigate I/O bottlenecks, ensuring high performance within user-specified resource constraints. Experiments demonstrate that FlexInfer significantly improves throughput under limited resources, achieving up to 12.5 times better performance than existing methods and facilitating the deployment of large models on resource-constrained devices.

Large vision-language models (VLMs) such as GPT-4 have achieved exceptional performance across various multi-modal tasks. However, the deployment of VLMs necessitates substantial energy consumption and computational resources. Once attackers maliciously induce high energy consumption and latency time (energy-latency cost) during inference of VLMs, it will exhaust computational resources. In this paper, we explore this attack surface about availability of VLMs and aim to induce high energy-latency cost during inference of VLMs. We find that high energy-latency cost during inference of VLMs can be manipulated by maximizing the length of generated sequences. To this end, we propose verbose images, with the goal of crafting an imperceptible perturbation to induce VLMs to generate long sentences during inference. Concretely, we design three loss objectives. First, a loss is proposed to delay the occurrence of end-of-sequence (EOS) token, where EOS token is a signal for VLMs to stop generating further tokens. Moreover, an uncertainty loss and a token diversity loss are proposed to increase the uncertainty over each generated token and the diversity among all tokens of the whole generated sequence, respectively, which can break output dependency at token-level and sequence-level. Furthermore, a temporal weight adjustment algorithm is proposed, which can effectively balance these losses. Extensive experiments demonstrate that our verbose images can increase the length of generated sequences by 7.87 times and 8.56 times compared to original images on MS-COCO and ImageNet datasets, which presents potential challenges for various applications. Our code is available at https://github.com/KuofengGao/Verbose_Images.

Although LLM inference has emerged as a critical workload for many downstream applications, efficiently inferring LLMs is challenging due to the substantial memory footprint and bandwidth requirements. In parallel, compute capabilities have steadily outpaced both memory capacity and bandwidth over the last few decades, a trend that remains evident in modern GPU hardware and exacerbates the challenge of LLM inference. As such, new algorithms are emerging that trade increased computation for reduced memory operations. To that end, we present XQuant, which takes advantage of this trend, enabling an order-of-magnitude reduction in memory consumption through low-bit quantization with substantial accuracy benefits relative to state-of-the-art KV cache quantization methods. We accomplish this by quantizing and caching the layer input activations X, instead of using standard KV caching, and then rematerializing the Keys and Values on-the-fly during inference. This results in an immediate 2times memory savings compared to KV caching. By applying XQuant, we achieve up to sim 7.7times memory savings with <0.1 perplexity degradation compared to the FP16 baseline. Furthermore, our approach leverages the fact that X values are similar across layers. Building on this observation, we introduce XQuant-CL, which exploits the cross-layer similarity in the X embeddings for extreme compression. Across different models, XQuant-CL attains up to 10times memory savings relative to the FP16 baseline with only 0.01 perplexity degradation, and 12.5times memory savings with only 0.1 perplexity degradation. XQuant exploits the rapidly increasing compute capabilities of hardware platforms to eliminate the memory bottleneck, while surpassing state-of-the-art KV cache quantization methods and achieving near-FP16 accuracy across a wide range of models.

Recent large language models (LLMs) have enabled the development of advanced agentic systems that can integrate various tools and APIs to fulfill user queries through function calling. However, the deployment of these LLMs on the edge has not been explored since they typically require cloud-based infrastructure due to their substantial model size and computational demands. To this end, we present TinyAgent, an end-to-end framework for training and deploying task-specific small language model agents capable of function calling for driving agentic systems at the edge. We first show how to enable accurate function calling for open-source models via the LLMCompiler framework. We then systematically curate a high-quality dataset for function calling, which we use to fine-tune two small language models, TinyAgent-1.1B and 7B. For efficient inference, we introduce a novel tool retrieval method to reduce the input prompt length and utilize quantization to further accelerate the inference speed. As a driving application, we demonstrate a local Siri-like system for Apple's MacBook that can execute user commands through text or voice input. Our results show that our models can achieve, and even surpass, the function-calling capabilities of larger models like GPT-4-Turbo, while being fully deployed at the edge. We open-source our dataset, models, and installable package and provide a demo video for our MacBook assistant agent.

We introduce CompAct, a technique that reduces peak memory utilization on GPU by 25-30% for pretraining and 50% for fine-tuning of LLMs. Peak device memory is a major limiting factor in training LLMs, with various recent works aiming to reduce model memory. However most works don't target the largest component of allocated memory during training: the model's compute graph, which is stored for the backward pass. By storing low-rank, compressed activations to be used in the backward pass we greatly reduce the required memory, unlike previous methods which only reduce optimizer overheads or the number of trained parameters. Our compression uses random projection matrices, thus avoiding additional memory overheads. Comparisons with previous techniques for either pretraining or fine-tuning show that CompAct substantially improves existing compute-performance tradeoffs. We expect CompAct's savings to scale even higher for larger models.

Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs: the first several blocks have an order of magnitude larger memory usage than the rest of the network. To alleviate this issue, we propose a generic patch-by-patch inference scheduling, which operates only on a small spatial region of the feature map and significantly cuts down the peak memory. However, naive implementation brings overlapping patches and computation overhead. We further propose network redistribution to shift the receptive field and FLOPs to the later stage and reduce the computation overhead. Manually redistributing the receptive field is difficult. We automate the process with neural architecture search to jointly optimize the neural architecture and inference scheduling, leading to MCUNetV2. Patch-based inference effectively reduces the peak memory usage of existing networks by 4-8x. Co-designed with neural networks, MCUNetV2 sets a record ImageNet accuracy on MCU (71.8%), and achieves >90% accuracy on the visual wake words dataset under only 32kB SRAM. MCUNetV2 also unblocks object detection on tiny devices, achieving 16.9% higher mAP on Pascal VOC compared to the state-of-the-art result. Our study largely addressed the memory bottleneck in tinyML and paved the way for various vision applications beyond image classification.

Test-time scaling seeks to improve the reasoning performance of large language models (LLMs) by adding computational resources. A prevalent approach within the field is sampling-based test-time scaling methods, which enhance reasoning by generating multiple reasoning paths for a given input during inference. However, despite its practical success, the theoretical foundations remain underexplored. In this paper, we provide the first theoretical framework for analyzing sampling-based test-time scaling methods, grounded in the perspective of confidence estimation. Based on the framework, we analyze two dominant paradigms: self-consistency and perplexity, and reveal key limitations: self-consistency suffers from high estimation error while perplexity exhibits substantial modeling error and possible degradation of the estimation error convergence. To address these limitations, we introduce RPC, a hybrid method that leverages our theoretical insights through two key components: Perplexity Consistency and Reasoning Pruning. Perplexity Consistency combines the strengths of self-consistency and perplexity, boosting the convergence rate of estimation error from linear to exponential while preserving model error. Reasoning Pruning prevents degradation by eliminating low-probability reasoning paths. Both theoretical analysis and empirical results across seven benchmark datasets demonstrate that RPC has a strong potential for reducing reasoning error. Notably, RPC achieves reasoning performance comparable to self-consistency while not only enhancing confidence reliability but also reducing sampling costs by 50%. The code and resources are available at https://wnjxyk.github.io/RPC.

Recent advancements in speculative decoding have demonstrated considerable speedup across a wide array of large language model (LLM) tasks. Speculative decoding inherently relies on sacrificing extra memory allocations to generate several candidate tokens, of which acceptance rate drives the speedup. However, deploying speculative decoding on memory-constrained devices, such as mobile GPUs, remains as a significant challenge in real-world scenarios. In this work, we present a device-aware inference engine named SpecMemo that can smartly control memory allocations at finer levels to enable multi-turn chatbots with speculative decoding on such limited memory devices. Our methodology stems from theoretically modeling memory footprint of speculative decoding to determine a lower bound on the required memory budget while retaining speedup. SpecMemo empirically acquires a careful balance between minimizing redundant memory allocations for rejected candidate tokens and maintaining competitive performance gains from speculation. Notably, with SpecMemo's memory management, we maintain 96% of overall throughput from speculative decoding on MT-Bench, with reduced generation-memory by 65% on single Nvidia Titan RTX. Given multiple constrained GPUs, we build on top of previous speculative decoding architectures to facilitate big-model inference by distributing Llama-2-70B-Chat model, on which we provide novel batched speculative decoding to increase usability of multiple small server GPUs. This novel framework demonstrates 2x speedup over distributed and batched vanilla decoding with the base model on eight AMD MI250 GPUs. Moreover, inference throughput increases remarkably 8x with batch size 10. Our work contributes to democratized LLM applications in resource-constrained environments, providing a pathway for faster and cheaper deployment of real-world LLM applications with robust performance.

Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to grow, posing challenges in latency and memory efficiency. To meet these constraints, post-training quantization has emerged as a promising solution. In this paper, we propose a novel hardware-efficient quantization and inference scheme that exploits hardware advantages with minimal accuracy degradation. Specifically, we introduce a W4A8 scheme, where weights are quantized and stored using 4-bit integer precision, and inference computations are performed using 8-bit floating-point arithmetic, demonstrating significant speedups and improved memory utilization compared to 16-bit operations, applicable on various modern accelerators. To mitigate accuracy loss, we develop a novel quantization algorithm, dubbed Dual Precision Quantization (DPQ), that leverages the unique structure of our scheme without introducing additional inference overhead. Experimental results demonstrate improved performance (i.e., increased throughput) while maintaining tolerable accuracy degradation relative to the full-precision model.

Large language models (LLMs) with hundreds of billions of parameters have sparked a new wave of exciting AI applications. However, they are computationally expensive at inference time. Sparsity is a natural approach to reduce this cost, but existing methods either require costly retraining, have to forgo LLM's in-context learning ability, or do not yield wall-clock time speedup on modern hardware. We hypothesize that contextual sparsity, which are small, input-dependent sets of attention heads and MLP parameters that yield approximately the same output as the dense model for a given input, can address these issues. We show that contextual sparsity exists, that it can be accurately predicted, and that we can exploit it to speed up LLM inference in wall-clock time without compromising LLM's quality or in-context learning ability. Based on these insights, we propose DejaVu, a system that uses a low-cost algorithm to predict contextual sparsity on the fly given inputs to each layer, along with an asynchronous and hardware-aware implementation that speeds up LLM inference. We validate that DejaVu can reduce the inference latency of OPT-175B by over 2X compared to the state-of-the-art FasterTransformer, and over 6X compared to the widely used Hugging Face implementation, without compromising model quality. The code is available at https://github.com/FMInference/DejaVu.

With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus. One effective approach is to compress the long input contexts. Existing methods typically leverage the self-attention mechanism of the LLM itself for context compression. While these methods have achieved notable results, the compression process still involves quadratic time complexity, which limits their applicability. To mitigate this limitation, we propose the In-Context Former (IC-Former). Unlike previous methods, IC-Former does not depend on the target LLMs. Instead, it leverages the cross-attention mechanism and a small number of learnable digest tokens to directly condense information from the contextual word embeddings. This approach significantly reduces inference time, which achieves linear growth in time complexity within the compression range. Experimental results indicate that our method requires only 1/32 of the floating-point operations of the baseline during compression and improves processing speed by 68 to 112 times while achieving over 90% of the baseline performance on evaluation metrics. Overall, our model effectively reduces compression costs and makes real-time compression scenarios feasible.

We show that the majority of the inference computations for large generative models such as LLaMA and OPT can be performed with both weights and activations being cast to 4 bits, in a way that leads to practical speedups while at the same time maintaining good accuracy. We achieve this via a hybrid quantization strategy called QUIK, which compresses most of the weights and activations to 4-bit, while keeping some outlier weights and activations in higher-precision. Crucially, our scheme is designed with computational efficiency in mind: we provide GPU kernels with highly-efficient layer-wise runtimes, which lead to practical end-to-end throughput improvements of up to 3.1x relative to FP16 execution. Code and models are provided at https://github.com/IST-DASLab/QUIK.

The sparse Mixture-of-Experts (MoE) model is powerful for large-scale pre-training and has achieved promising results due to its model capacity. However, with trillions of parameters, MoE is hard to be deployed on cloud or mobile environment. The inference of MoE requires expert parallelism, which is not hardware-friendly and communication expensive. Especially for resource-limited downstream tasks, such sparse structure has to sacrifice a lot of computing efficiency for limited performance gains. In this work, we observe most experts contribute scarcely little to the MoE fine-tuning and inference. We further propose a general method to progressively drop the non-professional experts for the target downstream task, which preserves the benefits of MoE while reducing the MoE model into one single-expert dense model. Our experiments reveal that the fine-tuned single-expert model could preserve 99.3% benefits from MoE across six different types of tasks while enjoying 2x inference speed with free communication cost.

Despite their strong performance on reasoning tasks, large reasoning models (LRMs) often suffer from overthinking, producing unnecessarily long outputs and incurring high end-to-end latency, a significant limitation to their real-world deployment. To address overthinking, early-exit mechanisms have been proposed to terminate reasoning before typical completion, showing that this approach can effectively shorten generation length with minimal impact on accuracy. However, their reliance on probing mechanisms introduces a detection overhead that limits their end-to-end latency gains and compromises their generalizability across diverse problems. Inspired by the use of hidden states in speculative decoding, we propose SpecExit, a novel framework that predicts both future tokens and an early-exit signal directly from a lightweight draft model without probing overhead. Our method offers significant improvements, reducing average generation length by 66\% and achieving a 2.5x speedup in end-to-end latency compared to the speculative decoding baseline, without compromising accuracy. Our method leverages the inherent signals from hidden states to provide effective early-exit signals, suggesting broader use of hidden states for efficient reasoning. Our code is available at https://github.com/Tencent/AngelSlim.

Large Language Models (LLMs) are becoming integral to daily life, showcasing their vast potential across various Natural Language Processing (NLP) tasks. Beyond NLP, LLMs are increasingly used in software development tasks, such as code completion, modification, bug fixing, and code translation. Software engineers widely use tools like GitHub Copilot and Amazon Q, streamlining workflows and automating tasks with high accuracy. While the resource and energy intensity of LLM training is often highlighted, inference can be even more resource-intensive over time, as it's a continuous process with a high number of invocations. Therefore, developing resource-efficient alternatives for LLM inference is crucial for sustainability. This work proposes GREEN-CODE, a framework for energy-aware code generation in LLMs. GREEN-CODE performs dynamic early exit during LLM inference. We train a Reinforcement Learning (RL) agent that learns to balance the trade-offs between accuracy, latency, and energy consumption. Our approach is evaluated on two open-source LLMs, Llama 3.2 3B and OPT 2.7B, using the JavaCorpus and PY150 datasets. Results show that our method reduces the energy consumption between 23-50 % on average for code generation tasks without significantly affecting accuracy.

Recent advances in large language models (LLMs) have accelerated progress toward artificial general intelligence, with inference-time scaling emerging as a key technique. Contemporary approaches leverage either sequential reasoning (iteratively extending chains of thought) or parallel reasoning (generating multiple solutions simultaneously) to scale inference. However, both paradigms face fundamental limitations: sequential scaling typically relies on arbitrary token budgets for termination, leading to inefficiency or premature cutoff; while parallel scaling often lacks coordination among parallel branches and requires intrusive fine-tuning to perform effectively. In light of these challenges, we aim to design a flexible test-time collaborative inference framework that exploits the complementary strengths of both sequential and parallel reasoning paradigms. Towards this goal, the core challenge lies in developing an efficient and accurate intrinsic quality metric to assess model responses during collaborative inference, enabling dynamic control and early termination of the reasoning trace. To address this challenge, we introduce semantic entropy (SE), which quantifies the semantic diversity of parallel model responses and serves as a robust indicator of reasoning quality due to its strong negative correlation with accuracy...

Recent advances in inference-time compute have significantly improved performance on complex tasks by generating long chains of thought (CoTs) using Large Reasoning Models (LRMs). However, this improved accuracy comes at the cost of high inference latency due to the length of generated reasoning sequences and the autoregressive nature of decoding. Our key insight in tackling these overheads is that LRM inference, and the reasoning that it embeds, is highly tolerant of approximations: complex tasks are typically broken down into simpler steps, each of which brings utility based on the semantic insight it provides for downstream steps rather than the exact tokens it generates. Accordingly, we introduce SpecReason, a system that automatically accelerates LRM inference by using a lightweight model to (speculatively) carry out simpler intermediate reasoning steps and reserving the costly base model only to assess (and potentially correct) the speculated outputs. Importantly, SpecReason's focus on exploiting the semantic flexibility of thinking tokens in preserving final-answer accuracy is complementary to prior speculation techniques, most notably speculative decoding, which demands token-level equivalence at each step. Across a variety of reasoning benchmarks, SpecReason achieves 1.5-2.5times speedup over vanilla LRM inference while improving accuracy by 1.0-9.9\%. Compared to speculative decoding without SpecReason, their combination yields an additional 19.4-44.2\% latency reduction. We open-source SpecReason at https://github.com/ruipeterpan/specreason.

Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost. We introduce sleep-time compute, which allows models to "think" offline about contexts before queries are presented: by anticipating what queries users might ask and pre-computing useful quantities, we can significantly reduce the compute requirements at test-time. To demonstrate the efficacy of our method, we create modified versions of two reasoning tasks - Stateful GSM-Symbolic and Stateful AIME. We find that sleep-time compute can reduce the amount of test-time compute needed to achieve the same accuracy by ~ 5x on Stateful GSM-Symbolic and Stateful AIME and that by scaling sleep-time compute we can further increase accuracy by up to 13% on Stateful GSM-Symbolic and 18% on Stateful AIME. Furthermore, we introduce Multi-Query GSM-Symbolic, which extends GSM-Symbolic by including multiple related queries per context. By amortizing sleep-time compute across related queries about the same context using Multi-Query GSM-Symbolic, we can decrease the average cost per query by 2.5x. We then conduct additional analysis to understand when sleep-time compute is most effective, finding the predictability of the user query to be well correlated with the efficacy of sleep-time compute. Finally, we conduct a case-study of applying sleep-time compute to a realistic agentic SWE task.

The e-commerce platform has evolved rapidly due to its widespread popularity and convenience. Developing an e-commerce shopping assistant for customers is crucial to aiding them in quickly finding desired products and recommending precisely what they need. However, most previous shopping assistants face two main problems: (1) task-specificity, which necessitates the development of different models for various tasks, thereby increasing development costs and limiting effectiveness; and (2) poor generalization, where the trained model performs inadequately on up-to-date products. To resolve these issues, we employ Large Language Models (LLMs) to construct an omnipotent assistant, leveraging their adeptness at handling multiple tasks and their superior generalization capability. Nonetheless, LLMs lack inherent knowledge of e-commerce concepts. To address this, we create an instruction dataset comprising 65,000 samples and diverse tasks, termed as EshopInstruct. Through instruction tuning on our dataset, the assistant, named LLaSA, demonstrates the potential to function as an omnipotent assistant. Additionally, we propose various inference optimization strategies to enhance performance with limited inference resources. In the Amazon KDD Cup 2024 Challenge, our proposed method, LLaSA, achieved an overall ranking of 3rd place on ShopBench, including 57 tasks and approximately 20,000 questions, and we secured top-5 rankings in each track, especially in track4, where we achieved the best performance result among all student teams. Our extensive practices fully demonstrate that LLMs possess the great potential to be competent e-commerce shopping assistants.

Transformer based models, like BERT and RoBERTa, have achieved state-of-the-art results in many Natural Language Processing tasks. However, their memory footprint, inference latency, and power consumption are prohibitive efficient inference at the edge, and even at the data center. While quantization can be a viable solution for this, previous work on quantizing Transformer based models use floating-point arithmetic during inference, which cannot efficiently utilize integer-only logical units such as the recent Turing Tensor Cores, or traditional integer-only ARM processors. In this work, we propose I-BERT, a novel quantization scheme for Transformer based models that quantizes the entire inference with integer-only arithmetic. Based on lightweight integer-only approximation methods for nonlinear operations, e.g., GELU, Softmax, and Layer Normalization, I-BERT performs an end-to-end integer-only BERT inference without any floating point calculation. We evaluate our approach on GLUE downstream tasks using RoBERTa-Base/Large. We show that for both cases, I-BERT achieves similar (and slightly higher) accuracy as compared to the full-precision baseline. Furthermore, our preliminary implementation of I-BERT shows a speedup of 2.4-4.0x for INT8 inference on a T4 GPU system as compared to FP32 inference. The framework has been developed in PyTorch and has been open-sourced.

Recent advancements in Large Language Model (LLM) compression, such as BitNet and BitNet b1.58, have marked significant strides in reducing the computational demands of LLMs through innovative one-bit quantization techniques. We extend this frontier by looking at Large Inference Models (LIMs) that have become indispensable across various applications. However, their scale and complexity often come at a significant computational cost. We introduce a novel approach that leverages one-bit algorithm unrolling, effectively integrating information from the physical world in the model architecture. Our method achieves a bit-per-link rate significantly lower than the 1.58 bits reported in prior work, thanks to the natural sparsity that emerges in our network architectures. We numerically demonstrate that the proposed one-bit algorithm unrolling scheme can improve both training and test outcomes by effortlessly increasing the number of layers while substantially compressing the network. Additionally, we provide theoretical results on the generalization gap, convergence rate, stability, and sensitivity of our proposed one-bit algorithm unrolling.

Scaling the test-time compute of large language models has demonstrated impressive performance on reasoning benchmarks. However, existing evaluations of test-time scaling make the strong assumption that a reasoning system should always give an answer to any question provided. This overlooks concerns about whether a model is confident in its answer, and whether it is appropriate to always provide a response. To address these concerns, we extract confidence scores during reasoning for thresholding model responses. We find that increasing compute budget at inference time not only helps models answer more questions correctly, but also increases confidence in correct responses. We then extend the current paradigm of zero-risk responses during evaluation by considering settings with non-zero levels of response risk, and suggest a recipe for reporting evaluations under these settings.

The inference phase of Large Language Models (LLMs) is very expensive. An ideal inference stage of LLMs could utilize fewer computational resources while still maintaining its capabilities (e.g., generalization and in-context learning ability). In this paper, we try to answer the question, "During LLM inference, can we use shallow layers for easy instances; and deep layers for hard ones?" To answer this question, we first indicate that Not all Layers are Necessary during Inference by statistically analyzing the activated layers across tasks. Then, we propose a simple algorithm named AdaInfer to determine the inference termination moment based on the input instance adaptively. More importantly, AdaInfer does not alter LLM parameters and maintains generalizability across tasks. Experiments on well-known LLMs (i.e., Llama2 series and OPT) show that AdaInfer saves an average of 14.8% of computational resources, even up to 50% on sentiment tasks, while maintaining comparable performance. Additionally, this method is orthogonal to other model acceleration techniques, potentially boosting inference efficiency further.

Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference, hindering their scalability for real-time applications like chatbots. To accelerate inference, we store computed keys and values (KV cache) in the GPU memory. Existing methods study the KV cache compression to reduce memory by pruning the pre-computed KV cache. However, they neglect the inter-layer dependency between layers and huge memory consumption in pre-computation. To explore these deficiencies, we find that the number of crucial keys and values that influence future generations decreases layer by layer and we can extract them by the consistency in attention weights. Based on the findings, we propose PyramidInfer, a method that compresses the KV cache by layer-wise retaining crucial context. PyramidInfer saves significant memory by computing fewer keys and values without sacrificing performance. Experimental results show PyramidInfer improves 2.2x throughput compared to Accelerate with over 54% GPU memory reduction in KV cache.

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained devices. In this paper, we investigate compression and efficient inference methods for large language models from an algorithmic perspective. Regarding taxonomy, similar to smaller models, compression and acceleration algorithms for large language models can still be categorized into quantization, pruning, distillation, compact architecture design, dynamic networks. However, Large language models have two prominent characteristics compared to smaller models: (1) Most of compression algorithms require finetuning or even retraining the model after compression. The most notable aspect of large models is the very high cost associated with model finetuning or training. Therefore, many algorithms for large models, such as quantization and pruning, start to explore tuning-free algorithms. (2) Large models emphasize versatility and generalization rather than performance on a single task. Hence, many algorithms, such as knowledge distillation, focus on how to preserving their versatility and generalization after compression. Since these two characteristics were not very pronounced in early large models, we further distinguish large language models into medium models and ``real'' large models. Additionally, we also provide an introduction to some mature frameworks for efficient inference of large models, which can support basic compression or acceleration algorithms, greatly facilitating model deployment for users.

Large language models (LLMs) propel the prosperity of interactive AI applications showcased by ChatGPT that demand timely response of inference services. However, LLM inference is computation intensive and memory intensive, and improper parameter configuration at LLM platforms may exacerbate the inference time. In this paper, we analyze the impact of LLM output token distribution on the inference queueing delay, where the max-token clipping and the batched inference are considered. By formulating an M/G/1 model, we observe that enforcing a maximum output token limit on a very small fraction of inference requests can significantly reduce the queueing delay, and our model facilitates the selection of the optimal limit. For the batch inference, we model the service process as a bulk queue in which the batch processing time is affected by the batch size and the maximum token size inside this batch jointly. The queueing delays of the batching of all buffered requests (dynamic batching), the batching of constant number of requests (fixed batching), and the batching without intra-batch waiting (elastic batching) are derived. Experimental results show that our mathematical models coincide with the event-driven simulations well.

Test-Time Scaling (TTS) is a promising approach to progressively elicit the model's intelligence during inference. Recently, training-based TTS methods, such as continued reinforcement learning (RL), have further surged in popularity, while training-free TTS methods are gradually fading from prominence. However, the additional computation overhead of training amplifies the burden on test-time scaling. In this paper, we focus on training-free TTS methods for reasoning. We first design Conditional Step-level Self-refinement, a fine-grained sequential scaling method guided by process verification. On top of its effectiveness, we further combine it with other classical parallel scaling methods at the step level, to introduce a novel inference paradigm called Hybrid Test-Time Scaling. Extensive experiments on five instruction-tuned LLMs across different scales (3B-14B) and families demonstrate that hybrid strategy incorporating various training-free TTS methods at a fine granularity has considerable potential for expanding the reasoning performance boundaries of LLMs.

Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a progressive inference paradigm over cloud and edge, i.e., firstly generating the sketch of the answer by LLMs at cloud, and then conducting parallel extension to fill in details by small models (SLMs) at edge. Progressive inference offers potential benefits to improve throughput and reduce inference latency while facing key implementation challenges, including decreased response quality from SLMs, a tradeoff between the brevity and comprehensiveness of sketches, as well as increased latency caused by network transmission and edge inference. In this work, we propose and implement PICE, an LLM serving system with semantic-level cloud-edge collaboration, enhancing inference throughput and quality through dynamic inference task scheduling, ensemble learning, and parallel edge inference. Extensive testbed experiments illustrate that our approach achieves 1.5-2times throughput enhancement and up to 43% latency reduction, while also potentially enhancing the quality compared to SOTA systems.

Recently, the idea of using FP8 as a number format for neural network training has been floating around the deep learning world. Given that most training is currently conducted with entire networks in FP32, or sometimes FP16 with mixed-precision, the step to having some parts of a network run in FP8 with 8-bit weights is an appealing potential speed-up for the generally costly and time-intensive training procedures in deep learning. A natural question arises regarding what this development means for efficient inference on edge devices. In the efficient inference device world, workloads are frequently executed in INT8. Sometimes going even as low as INT4 when efficiency calls for it. In this whitepaper, we compare the performance for both the FP8 and INT formats for efficient on-device inference. We theoretically show the difference between the INT and FP formats for neural networks and present a plethora of post-training quantization and quantization-aware-training results to show how this theory translates to practice. We also provide a hardware analysis showing that the FP formats are somewhere between 50-180% less efficient in terms of compute in dedicated hardware than the INT format. Based on our research and a read of the research field, we conclude that although the proposed FP8 format could be good for training, the results for inference do not warrant a dedicated implementation of FP8 in favor of INT8 for efficient inference. We show that our results are mostly consistent with previous findings but that important comparisons between the formats have thus far been lacking. Finally, we discuss what happens when FP8-trained networks are converted to INT8 and conclude with a brief discussion on the most efficient way for on-device deployment and an extensive suite of INT8 results for many models.

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that achieve full accuracy recovery for fine-tuning tasks at up to 70% sparsity. We achieve this for the LLaMA-2 7B model by combining the SparseGPT one-shot pruning method and sparse pretraining of those models on a subset of the SlimPajama dataset mixed with a Python subset of The Stack dataset. We exhibit training acceleration due to sparsity on Cerebras CS-3 chips that closely matches theoretical scaling. In addition, we establish inference acceleration of up to 3x on CPUs by utilizing Neural Magic's DeepSparse engine and 1.7x on GPUs through Neural Magic's nm-vllm engine. The above gains are realized via sparsity alone, thus enabling further gains through additional use of quantization. Specifically, we show a total speedup on CPUs for sparse-quantized LLaMA models of up to 8.6x. We demonstrate these results across diverse, challenging tasks, including chat, instruction following, code generation, arithmetic reasoning, and summarization to prove their generality. This work paves the way for rapidly creating smaller and faster LLMs without sacrificing accuracy.

Recent advancements in reasoning language models have demonstrated remarkable performance in complex tasks, but their extended chain-of-thought reasoning process increases inference overhead. While quantization has been widely adopted to reduce the inference cost of large language models, its impact on reasoning models remains understudied. In this study, we conduct the first systematic study on quantized reasoning models, evaluating the open-sourced DeepSeek-R1-Distilled Qwen and LLaMA families ranging from 1.5B to 70B parameters, and QwQ-32B. Our investigation covers weight, KV cache, and activation quantization using state-of-the-art algorithms at varying bit-widths, with extensive evaluation across mathematical (AIME, MATH-500), scientific (GPQA), and programming (LiveCodeBench) reasoning benchmarks. Our findings reveal that while lossless quantization can be achieved with W8A8 or W4A16 quantization, lower bit-widths introduce significant accuracy risks. We further identify model size, model origin, and task difficulty as critical determinants of performance. Contrary to expectations, quantized models do not exhibit increased output lengths. In addition, strategically scaling the model sizes or reasoning steps can effectively enhance the performance. All quantized models and codes will be open-sourced in https://github.com/ruikangliu/Quantized-Reasoning-Models.

Large reasoning models (LRMs) have recently achieved significant progress in complex reasoning tasks, aided by reinforcement learning with verifiable rewards. However, LRMs often suffer from overthinking, expending excessive computation on simple problems and reducing efficiency. Existing efficient reasoning methods typically require accurate task assessment to preset token budgets or select reasoning modes, which limits their flexibility and reliability. In this work, we revisit the essence of overthinking and identify that encouraging effective steps while penalizing ineffective ones is key to its solution. To this end, we propose a novel rule-based verifiable stepwise reward mechanism (VSRM), which assigns rewards based on the performance of intermediate states in the reasoning trajectory. This approach is intuitive and naturally fits the step-by-step nature of reasoning tasks. We conduct extensive experiments on standard mathematical reasoning benchmarks, including AIME24 and AIME25, by integrating VSRM with PPO and Reinforce++. Results show that our method achieves substantial output length reduction while maintaining original reasoning performance, striking an optimal balance between efficiency and accuracy. Further analysis of overthinking frequency and pass@k score before and after training demonstrates that our approach in deed effectively suppresses ineffective steps and encourages effective reasoning, fundamentally alleviating the overthinking problem. All code will be released upon acceptance.

To improve the efficiency of distributed large language model (LLM) inference, various parallelization strategies, such as tensor and pipeline parallelism, have been proposed. However, the distinct computational characteristics inherent in the two stages of LLM inference-prefilling and decoding-render a single static parallelization strategy insufficient for the effective optimization of both stages. In this work, we present Seesaw, an LLM inference engine optimized for throughput-oriented tasks. The key idea behind Seesaw is dynamic model re-sharding, a technique that facilitates the dynamic reconfiguration of parallelization strategies across stages, thereby maximizing throughput at both phases. To mitigate re-sharding overhead and optimize computational efficiency, we employ tiered KV cache buffering and transition-minimizing scheduling. These approaches work synergistically to reduce the overhead caused by frequent stage transitions while ensuring maximum batching efficiency. Our evaluation demonstrates that Seesaw achieves a throughput increase of up to 1.78x (1.36x on average) compared to vLLM, the most widely used state-of-the-art LLM inference engine.

Despite the impressive performance of LLMs, their widespread adoption faces challenges due to substantial computational and memory requirements during inference. Recent advancements in model compression and system-level optimization methods aim to enhance LLM inference. This survey offers an overview of these methods, emphasizing recent developments. Through experiments on LLaMA(/2)-7B, we evaluate various compression techniques, providing practical insights for efficient LLM deployment in a unified setting. The empirical analysis on LLaMA(/2)-7B highlights the effectiveness of these methods. Drawing from survey insights, we identify current limitations and discuss potential future directions to improve LLM inference efficiency. We release the codebase to reproduce the results presented in this paper at https://github.com/nyunAI/Faster-LLM-Survey

Given the generational gap in available hardware between lay practitioners and the most endowed institutions, LLMs are becoming increasingly inaccessible as they grow in size. Whilst many approaches have been proposed to compress LLMs to make their resource consumption manageable, these methods themselves tend to be resource intensive, putting them out of the reach of the very user groups they target. In this work, we explore the problem of structured pruning of LLMs using only forward passes. We seek to empower practitioners to prune models so large that their available hardware has just enough memory to run inference. We develop Bonsai, a gradient-free, perturbative pruning method capable of delivering small, fast, and accurate pruned models. We observe that Bonsai outputs pruned models that (i) outperform those generated by more expensive gradient-based structured pruning methods, and (ii) are twice as fast (with comparable accuracy) as those generated by semi-structured pruning methods requiring comparable resources as Bonsai. We also leverage Bonsai to produce a new sub-2B model using a single A6000 that yields state-of-the-art performance on 4/6 tasks on the Huggingface Open LLM leaderboard.

Reasoning large language models (LLMs) heavily rely on scaling test-time compute to perform complex reasoning tasks by generating extensive "thinking" chains. While demonstrating impressive results, this approach incurs significant computational costs and inference time. In this work, we challenge the assumption that long thinking chains results in better reasoning capabilities. We first demonstrate that shorter reasoning chains within individual questions are significantly more likely to yield correct answers - up to 34.5% more accurate than the longest chain sampled for the same question. Based on these results, we suggest short-m@k, a novel reasoning LLM inference method. Our method executes k independent generations in parallel and halts computation once the first m thinking processes are done. The final answer is chosen using majority voting among these m chains. Basic short-1@k demonstrates similar or even superior performance over standard majority voting in low-compute settings - using up to 40% fewer thinking tokens. short-3@k, while slightly less efficient than short-1@k, consistently surpasses majority voting across all compute budgets, while still being substantially faster (up to 33% wall time reduction). Inspired by our results, we finetune an LLM using short, long, and randomly selected reasoning chains. We then observe that training on the shorter ones leads to better performance. Our findings suggest rethinking current methods of test-time compute in reasoning LLMs, emphasizing that longer "thinking" does not necessarily translate to improved performance and can, counter-intuitively, lead to degraded results.

Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression techniques such as neural network pruning produces greater performance loss than in typical language modeling tasks, and in some cases can make the model slower since they cause the model to produce more thinking tokens but with worse performance. We show that this is partly due to the fact that standard LLM pruning methods often focus on input reconstruction, whereas reasoning is a decode-dominated task. We introduce a simple, drop-in fix: during pruning we jointly reconstruct activations from the input and the model's on-policy chain-of-thought traces. This "Reasoning-Aware Compression" (RAC) integrates seamlessly into existing pruning workflows such as SparseGPT, and boosts their performance significantly. Code reproducing the results in the paper can be found at: https://github.com/RyanLucas3/RAC

Despite advances in the programmable logic capabilities of modern trigger systems, a significant bottleneck remains in the amount of data to be transported from the detector to off-detector logic where trigger decisions are made. We demonstrate that a neural network autoencoder model can be implemented in a radiation tolerant ASIC to perform lossy data compression alleviating the data transmission problem while preserving critical information of the detector energy profile. For our application, we consider the high-granularity calorimeter from the CMS experiment at the CERN Large Hadron Collider. The advantage of the machine learning approach is in the flexibility and configurability of the algorithm. By changing the neural network weights, a unique data compression algorithm can be deployed for each sensor in different detector regions, and changing detector or collider conditions. To meet area, performance, and power constraints, we perform a quantization-aware training to create an optimized neural network hardware implementation. The design is achieved through the use of high-level synthesis tools and the hls4ml framework, and was processed through synthesis and physical layout flows based on a LP CMOS 65 nm technology node. The flow anticipates 200 Mrad of ionizing radiation to select gates, and reports a total area of 3.6 mm^2 and consumes 95 mW of power. The simulated energy consumption per inference is 2.4 nJ. This is the first radiation tolerant on-detector ASIC implementation of a neural network that has been designed for particle physics applications.

Sparse Mixture of Experts (MoE) models, while outperforming dense Large Language Models (LLMs) in terms of performance, face significant deployment challenges during inference due to their high memory demands. Existing offloading techniques, which involve swapping activated and idle experts between the GPU and CPU, often suffer from rigid expert caching mechanisms. These mechanisms fail to adapt to dynamic routing, leading to inefficient cache utilization, or incur prohibitive costs for prediction training. To tackle these inference-specific challenges, we introduce ExpertFlow, a comprehensive system specifically designed to enhance inference efficiency by accommodating flexible routing and enabling efficient expert scheduling between CPU and GPU. This reduces overhead and boosts system performance. Central to our approach is a predictive routing path-based offloading mechanism that utilizes a lightweight predictor to accurately forecast routing paths before computation begins. This proactive strategy allows for real-time error correction in expert caching, significantly increasing cache hit ratios and reducing the frequency of expert transfers, thereby minimizing I/O overhead. Additionally, we implement a dynamic token scheduling strategy that optimizes MoE inference by rearranging input tokens across different batches. This method not only reduces the number of activated experts per batch but also improves computational efficiency. Our extensive experiments demonstrate that ExpertFlow achieves up to 93.72\% GPU memory savings and enhances inference speed by 2 to 10 times compared to baseline methods, highlighting its effectiveness and utility as a robust solution for resource-constrained inference scenarios.

The size and compute characteristics of modern large language models have led to an increased interest in developing specialized kernels tailored for training and inference. Existing kernels primarily optimize for compute utilization, targeting the large-batch training and inference settings. However, low-batch inference, where memory bandwidth and kernel launch overheads contribute are significant factors, remains important for many applications of interest such as in edge deployment and latency-sensitive applications. This paper describes FlashFormer, a proof-of-concept kernel for accelerating single-batch inference for transformer-based large language models. Across various model sizes and quantizations settings, we observe nontrivial speedups compared to existing state-of-the-art inference kernels.

Deep learning is computationally intensive, with significant efforts focused on reducing arithmetic complexity, particularly regarding energy consumption dominated by data movement. While existing literature emphasizes inference, training is considerably more resource-intensive. This paper proposes a novel mathematical principle by introducing the notion of Boolean variation such that neurons made of Boolean weights and inputs can be trained -- for the first time -- efficiently in Boolean domain using Boolean logic instead of gradient descent and real arithmetic. We explore its convergence, conduct extensively experimental benchmarking, and provide consistent complexity evaluation by considering chip architecture, memory hierarchy, dataflow, and arithmetic precision. Our approach achieves baseline full-precision accuracy in ImageNet classification and surpasses state-of-the-art results in semantic segmentation, with notable performance in image super-resolution, and natural language understanding with transformer-based models. Moreover, it significantly reduces energy consumption during both training and inference.

It is widely acknowledged that the performance of Transformer models is exponentially related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from computational complexity, they still face challenges in inference due to high memory access costs. This work introduces UltraMem, incorporating large-scale, ultra-sparse memory layer to address these limitations. Our approach significantly reduces inference latency while maintaining model performance. We also investigate the scaling laws of this new architecture, demonstrating that it not only exhibits favorable scaling properties but outperforms traditional models. In our experiments, we train networks with up to 20 million memory slots. The results show that our method achieves state-of-the-art inference speed and model performance within a given computational budget.

Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. Unlike traditional model compression, which needs retraining, recent dynamic computation methods show that not all components are required for inference, enabling a training-free pipeline. In this paper, we focus on the dynamic depth of LLM generation. A token-position aware layer skipping framework is proposed to save 1.5x times operations efficiently while maintaining performance. We first observed that tokens predicted later have lower perplexity and thus require less computation. Then, we propose a training-free algorithm called Position-Aware Depth Decay Decoding (D^3), which leverages a power-law decay function, leftlfloor L times (alpha^i) rightrfloor, to determine the number of layers to retain when generating token T_i. Remarkably, without any retraining, the D^3 achieves success across a wide range of generation tasks for the first time. Experiments on large language models (\ie the Llama) with 7 sim 70 billion parameters show that D^3 can achieve an average 1.5x speedup compared with the full-inference pipeline while maintaining comparable performance with nearly no performance drop (<1%) on the GSM8K and BBH benchmarks.

Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system design and optimization opportunities. The technology is capable of understanding and responding in multiple modalities. However, the advanced capability currently comes with significant system resource demands. To sustainably scale generative AI capabilities to billions of users in the world, inference must be fast and efficient. This paper pinpoints key system design and optimization opportunities by characterizing a family of emerging multi-modal generation models on real systems. Auto-regressive token generation is a critical latency performance bottleneck, typically dominated by GPU idle time. In addition to memory-intensive attention across the generative AI models, linear operations constitute significant inference latency due to the feed forward networks in Transformer-based models. We demonstrate that state-of-the-art optimization levers, spanning from applications to system software and hardware, set a 3.88x better baseline.

The reasoning large language model (RLLM) has been proven competitive in solving complex reasoning tasks such as mathematics, coding, compared to general LLM. However, the serving performance and behavior of RLLM remains unexplored, which may undermine the deployment and utilization of RLLM in real-world scenario. To close this gap, in this paper, we conduct a comprehensive study of RLLM service. We first perform a pilot study on comparing the serving performance between RLLM and traditional LLM and reveal that there are several distinct differences regarding serving behavior: (1) significant memory usage and fluctuations; (2) straggler requests; (3) adaptive running time; (4) domain preference. Then we further investigate whether existing inference optimization techniques are valid for RLLM. Our main takeaways are that model quantization methods and speculative decoding can improve service system efficiency with small compromise to RLLM accuracy, while prefix caching, KV cache quantization may even degrade accuracy or serving performance for small RLLM. Lastly, we conduct evaluation under real world workload modeled by Gamma distribution to verify our findings. Empirical results of real world workload evaluation across different dataset are aligned with our main findings regarding RLLM serving. We hope our work can provide the research community and industry with insights to advance RLLM inference serving.

The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients' data privacy and security issues. Private inference (PI) techniques using cryptographic primitives offer a solution but often have high computation and communication costs, particularly with non-linear operators like ReLU. Many attempts to reduce ReLU operations exist, but they may need heuristic threshold selection or cause substantial accuracy loss. This work introduces AutoReP, a gradient-based approach to lessen non-linear operators and alleviate these issues. It automates the selection of ReLU and polynomial functions to speed up PI applications and introduces distribution-aware polynomial approximation (DaPa) to maintain model expressivity while accurately approximating ReLUs. Our experimental results demonstrate significant accuracy improvements of 6.12% (94.31%, 12.9K ReLU budget, CIFAR-10), 8.39% (74.92%, 12.9K ReLU budget, CIFAR-100), and 9.45% (63.69%, 55K ReLU budget, Tiny-ImageNet) over current state-of-the-art methods, e.g., SNL. Morever, AutoReP is applied to EfficientNet-B2 on ImageNet dataset, and achieved 75.55% accuracy with 176.1 times ReLU budget reduction.

Allocating more computation during inference time (test-time scaling) improves language model performance, especially for reasoning tasks. However, popular methods like Best-of-N sampling often show diminishing returns as N increases. To address this inefficiency, we introduce a general test-time calibration framework that adaptively modifies the model toward high-reward reasoning paths, with theoretical guarantees of improving the lower bound of expected reward under finite sampling, all without large language model (LLM) retraining. Within this framework, we propose CarBoN (Calibrated Best-of-N), a two-phase method that first explores the solution space and then learns a calibration of the logits via an input-specific temperature T and additive shift vector delta, guiding generation toward more reliable reasoning. Experiments on MATH-500 and AIME-2024 show that CarBoN improves efficiency, with up to 4times fewer rollouts to reach the same accuracy, while often achieving higher accuracy under fixed budgets. We also analyze the complementary roles of T and delta in balancing output diversity and correctness, and demonstrate that the framework also generalizes to step-level sampling strategies such as beam search. For more information, please refer to our project page at huggingface.co/spaces/TrustSafeAI/Test-Time-Calibration.

Chain-of-thought (CoT) prompting enhances reasoning in large language models (LLMs) but often leads to verbose and redundant outputs, thus increasing inference cost. We hypothesize that many reasoning steps are unnecessary for producing correct answers. To investigate this, we start with a systematic study to examine what is the minimum reasoning required for a model to reach a stable decision. We find that on math reasoning tasks like math, models typically converge to their final answers after 60\% of the reasoning steps, suggesting substantial redundancy in the remaining content. Based on these insights, we propose three inference-time strategies to improve efficiency: (1) early stopping via answer consistency, (2) boosting the probability of generating end-of-reasoning signals, and (3) a supervised method that learns when to stop based on internal activations. Experiments across five benchmarks and five open-weights LLMs show that our methods significantly reduce token usage with little or no accuracy drop. In particular, on NaturalQuestions, Answer Consistency reduces tokens by over 40\% while further improving accuracy. Our work underscores the importance of cost-effective reasoning methods that operate at inference time, offering practical benefits for real-world applications.

Large language models (LLMs) struggle with multi-step reasoning, where inference-time scaling has emerged as a promising strategy for performance improvement. Verifier-guided search outperforms repeated sampling when sample size is limited by selecting and prioritizing valid reasoning paths. However, we identify a critical limitation: scaling flaws, prevalent across different models (Mistral 7B and DeepSeekMath 7B), benchmarks (GSM8K and MATH), and verifiers (outcome value models and process reward models). As sample size increases, verifier-guided search exhibits diminishing advantages and eventually underperforms repeated sampling. Our analysis attributes this to verifier failures, where imperfect verifiers misrank candidates and erroneously prune all valid paths. These issues are further exacerbated in challenging and out-of-distribution problems, restricting search effectiveness. To mitigate verifier failures, we explore reducing reliance on verifiers and conduct preliminary investigations using two simple methods. Our findings reveal fundamental limitations in verifier-guided search and suggest future directions.

Existing safety assurance research has primarily focused on training-phase alignment to instill safe behaviors into LLMs. However, recent studies have exposed these methods' susceptibility to diverse jailbreak attacks. Concurrently, inference scaling has significantly advanced LLM reasoning capabilities but remains unexplored in the context of safety assurance. Addressing this gap, our work pioneers inference scaling for robust and effective LLM safety against emerging threats. We reveal that conventional inference scaling techniques, despite their success in reasoning tasks, perform poorly in safety contexts, even falling short of basic approaches like Best-of-N Sampling. We attribute this inefficiency to a newly identified challenge, the exploration--efficiency dilemma, arising from the high computational overhead associated with frequent process reward model (PRM) evaluations. To overcome this dilemma, we propose SAFFRON, a novel inference scaling paradigm tailored explicitly for safety assurance. Central to our approach is the introduction of a multifurcation reward model (MRM) that significantly reduces the required number of reward model evaluations. To operationalize this paradigm, we further propose: (i) a partial supervision training objective for MRM, (ii) a conservative exploration constraint to prevent out-of-distribution explorations, and (iii) a Trie-based key--value caching strategy that facilitates cache sharing across sequences during tree search. Extensive experiments validate the effectiveness of our method. Additionally, we publicly release our trained multifurcation reward model (Saffron-1) and the accompanying token-level safety reward dataset (Safety4M) to accelerate future research in LLM safety. Our code, model, and data are publicly available at https://github.com/q-rz/saffron , and our project homepage is at https://q-rz.github.io/p/saffron .

The large language model era urges faster and less costly inference. Prior model compression works on LLMs tend to undertake a software-centric approach primarily focused on the simulated quantization performance. By neglecting the feasibility of deployment, these approaches are typically disabled in real practice. They used to drastically push down the quantization bit range for a reduced computation which might not be supported by the mainstream hardware, or involve sophisticated algorithms that introduce extra computation or memory access overhead. We argue that pursuing a hardware-centric approach in the construction of quantization algorithms is crucial. In this regard, we are driven to build our compression method on top of hardware awareness, eliminating impractical algorithm choices while maximizing the benefit of hardware acceleration. Our method, OdysseyLLM, comes with a novel W4A8 kernel implementation called FastGEMM and a combined recipe of quantization strategies. Extensive experiments manifest the superiority of our W4A8 method which brings the actual speed boosting up to 4times compared to Hugging Face FP16 inference and 2.23times vs. the state-of-the-art inference engine TensorRT-LLM in FP16, and 1.45times vs. TensorRT-LLM in INT8, yet without substantially harming the performance.

We investigate an emerging setup in which a small, on-device language model (LM) with access to local data communicates with a frontier, cloud-hosted LM to solve real-world tasks involving financial, medical, and scientific reasoning over long documents. Can a local-remote collaboration reduce cloud inference costs while preserving quality? First, we consider a naive collaboration protocol where the local and remote models simply chat back and forth. Because only the local model reads the full context, this protocol achieves a 30.4x reduction in remote costs, but recovers only 87% of the performance of the frontier model. We identify two key limitations of this protocol: the local model struggles to (1) follow the remote model's multi-step instructions and (2) reason over long contexts. Motivated by these observations, we study an extension of this protocol, coined MinionS, in which the remote model decomposes the task into easier subtasks over shorter chunks of the document, that are executed locally in parallel. MinionS reduces costs by 5.7x on average while recovering 97.9% of the performance of the remote model alone. Our analysis reveals several key design choices that influence the trade-off between cost and performance in local-remote systems.

Recent research enhances language model reasoning by scaling test-time compute via longer chain-of-thought traces. This often improves accuracy but also introduces redundancy and high computational cost, especially for small language models distilled with supervised fine-tuning (SFT). In this work, we propose new algorithms to improve token-efficient reasoning with small-scale models by effectively trading off accuracy and computation. We first show that the post-SFT model fails to determine the optimal stopping point of the reasoning process, resulting in verbose and repetitive outputs. Verbosity also significantly varies across wrong vs correct responses. To address these issues, we propose two solutions: (1) Temperature scaling (TS) to control the stopping point for the thinking phase and thereby trace length, and (2) TLDR: a length-regularized reinforcement learning method based on GRPO that facilitates multi-level trace length control (e.g. short, medium, long reasoning). Experiments on four reasoning benchmarks, MATH500, AMC, AIME24 and OlympiadBench, demonstrate that TS is highly effective compared to s1's budget forcing approach and TLDR significantly improves token efficiency by about 50% with minimal to no accuracy loss over the SFT baseline. Moreover, TLDR also facilitates flexible control over the response length, offering a practical and effective solution for token-efficient reasoning in small models. Ultimately, our work reveals the importance of stopping time control, highlights shortcomings of pure SFT, and provides effective algorithmic recipes.

Reinforcement learning (RL) systems have countless applications, from energy-grid management to protein design. However, such real-world scenarios are often extremely difficult, combinatorial in nature, and require complex coordination between multiple agents. This level of complexity can cause even state-of-the-art RL systems, trained until convergence, to hit a performance ceiling which they are unable to break out of with zero-shot inference. Meanwhile, many digital or simulation-based applications allow for an inference phase that utilises a specific time and compute budget to explore multiple attempts before outputting a final solution. In this work, we show that such an inference phase employed at execution time, and the choice of a corresponding inference strategy, are key to breaking the performance ceiling observed in complex multi-agent RL problems. Our main result is striking: we can obtain up to a 126% and, on average, a 45% improvement over the previous state-of-the-art across 17 tasks, using only a couple seconds of extra wall-clock time during execution. We also demonstrate promising compute scaling properties, supported by over 60k experiments, making it the largest study on inference strategies for complex RL to date. Our experimental data and code are available at https://sites.google.com/view/inf-marl.

There is intense interest in investigating how inference time compute (ITC) (e.g. repeated sampling, refinements, etc) can improve large language model (LLM) capabilities. At the same time, recent breakthroughs in reasoning models, such as Deepseek-R1, unlock the opportunity for reinforcement learning to improve LLM reasoning skills. An in-depth understanding of how ITC interacts with reasoning across different models could provide important guidance on how to further advance the LLM frontier. This work conducts a comprehensive analysis of inference-time scaling methods for both reasoning and non-reasoning models on challenging reasoning tasks. Specifically, we focus our research on verifier-free inference time-scaling methods due to its generalizability without needing a reward model. We construct the Pareto frontier of quality and efficiency. We find that non-reasoning models, even with an extremely high inference budget, still fall substantially behind reasoning models. For reasoning models, majority voting proves to be a robust inference strategy, generally competitive or outperforming other more sophisticated ITC methods like best-of-N and sequential revisions, while the additional inference compute offers minimal improvements. We further perform in-depth analyses of the association of key response features (length and linguistic markers) with response quality, with which we can improve the existing ITC methods. We find that correct responses from reasoning models are typically shorter and have fewer hedging and thinking markers (but more discourse markers) than the incorrect responses.

Large Language Models (LLMs) based on Mixture-of-Experts (MoE) architecture are showing promising performance on various tasks. However, running them on resource-constrained settings, where GPU memory resources are not abundant, is challenging due to huge model sizes. Existing systems that offload model weights to CPU memory suffer from the significant overhead of frequently moving data between CPU and GPU. In this paper, we propose Fiddler, a resource-efficient inference engine with CPU-GPU orchestration for MoE models. The key idea of Fiddler is to use the computation ability of the CPU to minimize the data movement between the CPU and GPU. Our evaluation shows that Fiddler can run the uncompressed Mixtral-8x7B model, which exceeds 90GB in parameters, to generate over 3 tokens per second on a single GPU with 24GB memory, showing an order of magnitude improvement over existing methods. The code of Fiddler is publicly available at https://github.com/efeslab/fiddler

The privacy concerns of providing deep learning inference as a service have underscored the need for private inference (PI) protocols that protect users' data and the service provider's model using cryptographic methods. Recently proposed PI protocols have achieved significant reductions in PI latency by moving the computationally heavy homomorphic encryption (HE) parts to an offline/pre-compute phase. Paired with recent optimizations that tailor networks for PI, these protocols have achieved performance levels that are tantalizingly close to being practical. In this paper, we conduct a rigorous end-to-end characterization of PI protocols and optimization techniques and find that the current understanding of PI performance is overly optimistic. Specifically, we find that offline storage costs of garbled circuits (GC), a key cryptographic protocol used in PI, on user/client devices are prohibitively high and force much of the expensive offline HE computation to the online phase, resulting in a 10-1000times increase to PI latency. We propose a modified PI protocol that significantly reduces client-side storage costs for a small increase in online latency. Evaluated end-to-end, the modified protocol outperforms current protocols by reducing the mean PI latency by 4times for ResNet18 on TinyImageNet. We conclude with a discussion of several recently proposed PI optimizations in light of the findings and note many actually increase PI latency when evaluated from an end-to-end perspective.

Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they afford in practice. An emerging strand of work empirically estimates the protection afforded by differentially private training as a confidence interval for the privacy budget varepsilon spent on training a model. Existing approaches derive confidence intervals for varepsilon from confidence intervals for the false positive and false negative rates of membership inference attacks. Unfortunately, obtaining narrow high-confidence intervals for epsilon using this method requires an impractically large sample size and training as many models as samples. We propose a novel Bayesian method that greatly reduces sample size, and adapt and validate a heuristic to draw more than one sample per trained model. Our Bayesian method exploits the hypothesis testing interpretation of differential privacy to obtain a posterior for varepsilon (not just a confidence interval) from the joint posterior of the false positive and false negative rates of membership inference attacks. For the same sample size and confidence, we derive confidence intervals for varepsilon around 40% narrower than prior work. The heuristic, which we adapt from label-only DP, can be used to further reduce the number of trained models needed to get enough samples by up to 2 orders of magnitude.

Scaling the number of parameters and the size of training data has proven to be an effective strategy for improving large language model (LLM) performance. Yet, as these models grow increasingly powerful and widely deployed, the cost of inference has become a pressing concern. Despite its importance, the trade-off between model accuracy and inference efficiency remains underexplored. In this work, we examine how key architectural factors, hidden size, the allocation of parameters between MLP and attention (mlp-to-attention ratio), and grouped-query attention (GQA), influence both inference cost and accuracy. We introduce a conditional scaling law that augments the Chinchilla framework with architectural information, along with a search framework for identifying architectures that are simultaneously inference-efficient and accurate. To validate our approach, we train more than 200 models spanning 80M to 3B parameters and 8B to 100B training tokens, and fit the proposed conditional scaling law. Our results show that the conditional scaling law reliably predicts optimal architectural choices and that the resulting models outperform existing open-source baselines. Under the same training budget, optimized architectures achieve up to 2.1% higher accuracy and 42% greater inference throughput compared to LLaMA-3.2.

3D graphics editing is crucial in applications like movie production and game design, yet it remains a time-consuming process that demands highly specialized domain expertise. Automating this process is challenging because graphical editing requires performing a variety of tasks, each requiring distinct skill sets. Recently, vision-language models (VLMs) have emerged as a powerful framework for automating the editing process, but their development and evaluation are bottlenecked by the lack of a comprehensive benchmark that requires human-level perception and presents real-world editing complexity. In this work, we present BlenderGym, the first comprehensive VLM system benchmark for 3D graphics editing. BlenderGym evaluates VLM systems through code-based 3D reconstruction tasks. We evaluate closed- and open-source VLM systems and observe that even the state-of-the-art VLM system struggles with tasks relatively easy for human Blender users. Enabled by BlenderGym, we study how inference scaling techniques impact VLM's performance on graphics editing tasks. Notably, our findings reveal that the verifier used to guide the scaling of generation can itself be improved through inference scaling, complementing recent insights on inference scaling of LLM generation in coding and math tasks. We further show that inference compute is not uniformly effective and can be optimized by strategically distributing it between generation and verification.

Large Language Models (LLMs) have showcased remarkable capabilities across various domains. Accompanying the evolving capabilities and expanding deployment scenarios of LLMs, their deployment challenges escalate due to their sheer scale and the advanced yet complex activation designs prevalent in notable model series, such as Llama, Gemma, and Mistral. These challenges have become particularly pronounced in resource-constrained deployment scenarios, where mitigating inference efficiency bottlenecks is imperative. Among various recent efforts, activation approximation has emerged as a promising avenue for pursuing inference efficiency, sometimes considered indispensable in applications such as private inference. Despite achieving substantial speedups with minimal impact on utility, even appearing sound and practical for real-world deployment, the safety implications of activation approximations remain unclear. In this work, we fill this critical gap in LLM safety by conducting the first systematic safety evaluation of activation approximations. Our safety vetting spans seven sota techniques across three popular categories, revealing consistent safety degradation across ten safety-aligned LLMs.

In recent years, Transformer-based language models have become the standard approach for natural language processing tasks. However, stringent throughput and latency requirements in industrial applications are limiting their adoption. To mitigate the gap, model compression techniques such as structured pruning are being used to improve inference efficiency. However, most existing neural network inference runtimes lack adequate support for structured sparsity. In this paper, we propose an efficient sparse deep learning inference software stack for Transformer-based language models where the weights are pruned with constant block size. Our sparse software accelerator leverages Intel Deep Learning Boost to maximize the performance of sparse matrix - dense matrix multiplication (commonly abbreviated as SpMM) on CPUs. Our SpMM kernel outperforms the existing sparse libraries (oneMKL, TVM, and LIBXSMM) by an order of magnitude on a wide range of GEMM shapes under 5 representative sparsity ratios (70%, 75%, 80%, 85%, 90%). Moreover, our SpMM kernel shows up to 5x speedup over dense GEMM kernel of oneDNN, a well-optimized dense library widely used in industry. We apply our sparse accelerator on widely-used Transformer-based language models including Bert-Mini, DistilBERT, Bert-Base, and BERT-Large. Our sparse inference software shows up to 1.5x speedup over Neural Magic's Deepsparse under same configurations on Xeon on Amazon Web Services under proxy production latency constraints. We also compare our solution with two framework-based inference solutions, ONNX Runtime and PyTorch, and demonstrate up to 37x speedup over ONNX Runtime and 345x over PyTorch on Xeon under the latency constraints. All the source code is publicly available on Github: https://github.com/intel/intel-extension-for-transformers.

The growing computational demands of large language models (LLMs) make efficient inference and activation strategies increasingly critical. While recent approaches, such as Mixture-of-Experts (MoE), leverage selective activation but require specialized training, training-free sparse activation methods offer broader applicability and superior resource efficiency through their plug-and-play design. However, many existing methods rely solely on hidden state magnitudes to determine activation, resulting in high approximation errors and suboptimal inference accuracy. To address these limitations, we propose WINA (Weight Informed Neuron Activation), a novel, simple, and training-free sparse activation framework that jointly considers hidden state magnitudes and the column-wise ell_2-norms of weight matrices. We show that this leads to a sparsification strategy that obtains optimal approximation error bounds with theoretical guarantees tighter than existing techniques. Empirically, WINA also outperforms state-of-the-art methods (e.g., TEAL) by up to 2.94% in average performance at the same sparsity levels, across a diverse set of LLM architectures and datasets. These results position WINA as a new performance frontier for training-free sparse activation in LLM inference, advancing training-free sparse activation methods and setting a robust baseline for efficient inference. The source code is available at https://github.com/microsoft/wina.

Mixture-of-Experts (MoE) models scale efficiently by activating only a subset of experts per token, offering a computationally sparse alternative to dense architectures. While prior post-training optimizations, such as inter- and intra-expert pruning, reduce memory usage they provide limited gains in inference-time compute efficiency. Moreover, existing MoE architectures typically activate a fixed number of experts uniformly across all layers, resulting in redundant computation and suboptimal performance. In this work, we first demonstrate that MoE pruning strategies improve only the memory footprint but do not significantly improve inference performance on GPU using optimized frameworks such as vLLM. To address this, we introduce LExI, a data-free optimization technique that determines the optimal number of active experts per layer in a pretrained MoE model. LExI leverages only the model weights to estimate the relative importance of each layer and adaptively assigns the number of active experts accordingly per layer. Experiments on state-of-the-art language and vision MoE benchmarks demonstrate that LExI significantly outperforms traditional MoE pruning approaches in terms of inference efficiency with negligible accuracy loss. For example, using LExI, Qwen1.5-MoE achieves the same throughput on Nvidia H100 GPU with 10% better accuracy than traditional expert pruning.

Large Reasoning Models (LRMs) are criticized for the excessively lengthy Chain-of-Thought (CoT) to derive the final answer, suffering from high first-token and overall latency. Typically, the CoT of LRMs mixes multiple thinking units; each unit attempts to produce a candidate answer to the original query. Hence, a natural idea to improve efficiency is to reduce the unit number. Yet, the fact that the thinking units in vanilla CoT cannot be explicitly managed renders doing so challenging. This paper introduces Multi-Turn Decomposition (MinD) to decode conventional CoT into a sequence of explicit, structured, and turn-wise interactions to bridge the gap. In MinD, the model provides a multi-turn response to the query, where each turn embraces a thinking unit and yields a corresponding answer. The subsequent turns can reflect, verify, revise, or explore alternative approaches to both the thinking and answer parts of earlier ones. This not only makes the answer delivered more swiftly, but also enables explicit controls over the iterative reasoning process (i.e., users may halt or continue at any turn). We follow a supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm to realize MinD. We first rephrase the outputs of an LRM into multi-turn formats by prompting another LLM, and then tune the LRM with such data. Observing that the tuned model tends to consume even more tokens than the original one (probably due to that the multi-turn formats introduce additional answer tokens), we advocate leveraging RL algorithms like GRPO to prioritize correct outputs with fewer turns. Trained on the MATH dataset using R1-Distill models, MinD can achieve up to ~70% reduction in both output token usage and time to first token (TTFT), while maintaining competitive performance on reasoning benchmarks such as MATH-500, AIME24, AMC23, and GPQA-Diamond.

Mixture-of-Experts (MoE) has demonstrated promising potential in scaling LLMs. However, it is hindered by two critical challenges: (1) substantial GPU memory consumption to load all experts; (2) low activated parameters cannot be equivalently translated into inference acceleration effects. In this work, we propose EAC-MoE, an Expert-Selection Aware Compressor for MoE-LLMs, which deeply aligns with the characteristics of MoE from the perspectives of quantization and pruning, and introduces two modules to address these two challenges respectively: (1) The expert selection bias caused by low-bit quantization is a major factor contributing to the performance degradation in MoE-LLMs. Based on this, we propose Quantization with Expert-Selection Calibration (QESC), which mitigates the expert selection bias by calibrating the routers within the MoE; (2) There are always certain experts that are not crucial for the corresponding tasks, yet causing inference latency. Therefore, we propose Pruning based on Expert-Selection Frequency (PESF), which significantly improves inference speed by pruning less frequently used experts for current task. Extensive experiments demonstrate that our approach significantly reduces memory usage and improves inference speed with minimal performance degradation.

To accelerate the inference of heavy Multimodal Large Language Models (MLLMs), this study rethinks the current landscape of training-free token reduction research. We regret to find that the critical components of existing methods are tightly intertwined, with their interconnections and effects remaining unclear for comparison, transfer, and expansion. Therefore, we propose a unified ''filter-correlate-compress'' paradigm that decomposes the token reduction into three distinct stages within a pipeline, maintaining consistent design objectives and elements while allowing for unique implementations. We additionally demystify the popular works and subsume them into our paradigm to showcase its universality. Finally, we offer a suite of methods grounded in the paradigm, striking a balance between speed and accuracy throughout different phases of the inference. Experimental results across 10 benchmarks indicate that our methods can achieve up to an 82.4% reduction in FLOPs with a minimal impact on performance, simultaneously surpassing state-of-the-art training-free methods. Our project page is at https://ficoco-accelerate.github.io/.

Leveraging recent advancements in large language models, modern neural code completion models have demonstrated the capability to generate highly accurate code suggestions. However, their massive size poses challenges in terms of computational costs and environmental impact, hindering their widespread adoption in practical scenarios. Dynamic inference emerges as a promising solution, as it allocates minimal computation during inference while maintaining the model's performance. In this research, we explore dynamic inference within the context of code completion. Initially, we conducted an empirical investigation on GPT-2, focusing on the inference capabilities of intermediate layers for code completion. We found that 54.4% of tokens can be accurately generated using just the first layer, signifying significant computational savings potential. Moreover, despite using all layers, the model still fails to predict 14.5% of tokens correctly, and the subsequent completions continued from them are rarely considered helpful, with only a 4.2% Acceptance Rate. These findings motivate our exploration of dynamic inference in code completion and inspire us to enhance it with a decision-making mechanism that stops the generation of incorrect code. We thus propose a novel dynamic inference method specifically tailored for code completion models. This method aims not only to produce correct predictions with largely reduced computation but also to prevent incorrect predictions proactively. Our extensive evaluation shows that it can averagely skip 1.7 layers out of 16 layers in the models, leading to an 11.2% speedup with only a marginal 1.1% reduction in ROUGE-L.

Distributed inference of large language models (LLMs) can introduce overheads of up to 20% even over GPUs connected via high-speed interconnects such as NVLINK. Multiple techniques have been proposed to mitigate these overheads by decomposing computations into finer-grained tasks and overlapping communication with sub-tasks as they complete. However, fine-grained decomposition of a large computation into many smaller computations on GPUs results in overheads. Further, the communication itself uses many streaming multiprocessors (SMs), adding to the overhead. We present TokenWeave to address these challenges. TokenWeave proposes a Token-Splitting technique that divides the tokens in the inference batch into two approximately equal subsets in a wave-aware manner. The computation of one subset is then overlapped with the communication of the other. In addition, TokenWeave optimizes the order of the layer normalization computation with respect to communication operations and implements a novel fused AllReduce-RMSNorm kernel carefully leveraging Multimem instruction support available on NVIDIA Hopper GPUs. These optimizations allow TokenWeave to perform communication and RMSNorm using only 2-8 SMs. Moreover, our kernel enables the memory bound RMSNorm to be overlapped with the other batch's computation, providing additional gains. Our evaluations demonstrate up to 29% latency gains and up to 26% throughput gains across multiple models and workloads. In several settings, TokenWeave results in better performance compared to an equivalent model with all communication removed.

Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly acute for test-time scaling methods such as parallel decoding, which increase answer diversity but scale poorly in efficiency. To address this efficiency-accuracy trade-off, we propose SSR (Speculative Parallel Scaling Reasoning), a training-free framework that leverages a key insight: by introducing speculative decoding at the step level, we can accelerate reasoning without sacrificing correctness. SSR integrates two components: a Selective Parallel Module (SPM) that identifies a small set of promising reasoning strategies via model-internal scoring, and Step-level Speculative Decoding (SSD), which enables efficient draft-target collaboration for fine-grained reasoning acceleration. Experiments on three mathematical benchmarks-AIME 2024, MATH-500, and LiveMathBench - demonstrate that SSR achieves strong gains over baselines. For instance, on LiveMathBench, SSR improves pass@1 accuracy by 13.84% while reducing computation to 80.5% of the baseline FLOPs. On MATH-500, SSR reduces compute to only 30% with no loss in accuracy.

The widespread adoption of machine learning algorithms necessitates hardware acceleration to ensure efficient performance. This acceleration relies on custom matrix engines that operate on full or reduced-precision floating-point arithmetic. However, conventional floating-point implementations can be power hungry. This paper proposes a method to improve the energy efficiency of the matrix engines used in machine learning algorithm acceleration. Our approach leverages approximate normalization within the floating-point multiply-add units as a means to reduce their hardware complexity, without sacrificing overall machine-learning model accuracy. Hardware synthesis results show that this technique reduces area and power consumption roughly by 16% and 13% on average for Bfloat16 format. Also, the error introduced in transformer model accuracy is 1% on average, for the most efficient configuration of the proposed approach.

Large Language models (LLMs) have become a research hotspot. To accelerate the inference of LLMs, storing computed caches in memory has become the standard technique. However, as the inference length increases, growing KV caches might lead to out-of-memory issues. Many existing methods address this issue through KV cache compression, primarily by preserving key tokens throughout all layers to reduce information loss. Most of them allocate a uniform budget size for each layer to retain. However, we observe that the minimum budget sizes needed to retain essential information vary across layers and models based on the perspectives of attention and hidden state output. Building on this observation, this paper proposes a simple yet effective KV cache compression method that leverages layer uncertainty to allocate budget size for each layer. Experimental results show that the proposed method can reduce memory usage of the KV caches to only sim20\% when compared to Full KV inference while achieving nearly lossless performance.

Self-supervised learning (SSL) models like WavLM can be effectively utilized when building speaker diarization systems but are often large and slow, limiting their use in resource constrained scenarios. Previous studies have explored compression techniques, but usually for the price of degraded performance at high pruning ratios. In this work, we propose to compress SSL models through structured pruning by introducing knowledge distillation. Different from the existing works, we emphasize the importance of fine-tuning SSL models before pruning. Experiments on far-field single-channel AMI, AISHELL-4, and AliMeeting datasets show that our method can remove redundant parameters of WavLM Base+ and WavLM Large by up to 80% without any performance degradation. After pruning, the inference speeds on a single GPU for the Base+ and Large models are 4.0 and 2.6 times faster, respectively. Our source code is publicly available.

Scaling laws are powerful tools to predict the performance of large language models. However, current scaling laws fall short of accounting for inference costs. In this work, we first show that model architecture affects inference latency, where models of the same size can have up to 3.5x difference in latency. To tackle this challenge, we modify the Chinchilla scaling laws to co-optimize the model parameter count, the number of training tokens, and the model architecture. Due to the reason that models of similar training loss exhibit gaps in downstream evaluation, we also propose a novel method to train inference-efficient models based on the revised scaling laws. We perform extensive empirical studies to fit and evaluate our inference-aware scaling laws. We vary model parameters from 80M to 1B, training tokens from 1.6B to 30B, and model shapes, training a total of 63 models. Guided by our inference-efficient scaling law and model selection method, we release the Morph-1B model, which improves inference latency by 1.8x while maintaining accuracy on downstream tasks compared to open-source models, pushing the Pareto frontier of accuracy-latency tradeoff.

The new paradigm of test-time scaling has yielded remarkable breakthroughs in Large Language Models (LLMs) (e.g. reasoning models) and in generative vision models, allowing models to allocate additional computation during inference to effectively tackle increasingly complex problems. Despite the improvements of this approach, an important limitation emerges: the substantial increase in computation time makes the process slow and impractical for many applications. Given the success of this paradigm and its growing usage, we seek to preserve its benefits while eschewing the inference overhead. In this work we propose one solution to the critical problem of integrating test-time scaling knowledge into a model during post-training. Specifically, we replace reward guided test-time noise optimization in diffusion models with a Noise Hypernetwork that modulates initial input noise. We propose a theoretically grounded framework for learning this reward-tilted distribution for distilled generators, through a tractable noise-space objective that maintains fidelity to the base model while optimizing for desired characteristics. We show that our approach recovers a substantial portion of the quality gains from explicit test-time optimization at a fraction of the computational cost. Code is available at https://github.com/ExplainableML/HyperNoise

Large Language Models (LLMs) are now integral across various domains and have demonstrated impressive performance. Progress, however, rests on the premise that benchmark scores are both accurate and reproducible. We demonstrate that the reproducibility of LLM performance is fragile: changing system configuration such as evaluation batch size, GPU count, and GPU version can introduce significant difference in the generated responses. This issue is especially pronounced in reasoning models, where minor rounding differences in early tokens can cascade into divergent chains of thought, ultimately affecting accuracy. For instance, under bfloat16 precision with greedy decoding, a reasoning model like DeepSeek-R1-Distill-Qwen-7B can exhibit up to 9% variation in accuracy and 9,000 tokens difference in response length due to differences in GPU count, type, and evaluation batch size. We trace the root cause of this variability to the non-associative nature of floating-point arithmetic under limited numerical precision. This work presents the first systematic investigation into how numerical precision affects reproducibility in LLM inference. Through carefully controlled experiments across various hardware, software, and precision settings, we quantify when and how model outputs diverge. Our analysis reveals that floating-point precision -- while critical for reproducibility -- is often neglected in evaluation practices. Inspired by this, we develop a lightweight inference pipeline, dubbed LayerCast, that stores weights in 16-bit precision but performs all computations in FP32, balancing memory efficiency with numerical stability. Code is available at https://github.com/nanomaoli/llm_reproducibility.

As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemotron-H, a family of 8B and 56B/47B hybrid Mamba-Transformer models designed to reduce inference cost for a given accuracy level. To achieve this goal, we replace the majority of self-attention layers in the common Transformer model architecture with Mamba layers that perform constant computation and require constant memory per generated token. We show that Nemotron-H models offer either better or on-par accuracy compared to other similarly-sized state-of-the-art open-sourced Transformer models (e.g., Qwen-2.5-7B/72B and Llama-3.1-8B/70B), while being up to 3times faster at inference. To further increase inference speed and reduce the memory required at inference time, we created Nemotron-H-47B-Base from the 56B model using a new compression via pruning and distillation technique called MiniPuzzle. Nemotron-H-47B-Base achieves similar accuracy to the 56B model, but is 20% faster to infer. In addition, we introduce an FP8-based training recipe and show that it can achieve on par results with BF16-based training. This recipe is used to train the 56B model. All Nemotron-H models will be released, with support in Hugging Face, NeMo, and Megatron-LM.

In recent years, language models have drastically grown in size, and the abilities of these models have been shown to improve with scale. The majority of recent scaling laws studies focused on high-compute high-parameter count settings, leaving the question of when these abilities begin to emerge largely unanswered. In this paper, we investigate whether the effects of pre-training can be observed when the problem size is reduced, modeling a smaller, reduced-vocabulary language. We show the benefits of pre-training with masked language modeling (MLM) objective in models as small as 1.25M parameters, and establish a strong correlation between pre-training perplexity and downstream performance (GLUE benchmark). We examine downscaling effects, extending scaling laws to models as small as ~1M parameters. At this scale, we observe a break of the power law for compute-optimal models and show that the MLM loss does not scale smoothly with compute-cost (FLOPs) below 2.2 times 10^{15} FLOPs. We also find that adding layers does not always benefit downstream performance.

As large language models gain widespread adoption, running them efficiently becomes crucial. Recent works on LLM inference use speculative decoding to achieve extreme speedups. However, most of these works implicitly design their algorithms for high-end datacenter hardware. In this work, we ask the opposite question: how fast can we run LLMs on consumer machines? Consumer GPUs can no longer fit the largest available models (50B+ parameters) and must offload them to RAM or SSD. When running with offloaded parameters, the inference engine can process batches of hundreds or thousands of tokens at the same time as just one token, making it a natural fit for speculative decoding. We propose SpecExec (Speculative Execution), a simple parallel decoding method that can generate up to 20 tokens per target model iteration for popular LLM families. It utilizes the high spikiness of the token probabilities distribution in modern LLMs and a high degree of alignment between model output probabilities. SpecExec takes the most probable tokens continuation from the draft model to build a "cache" tree for the target model, which then gets validated in a single pass. Using SpecExec, we demonstrate inference of 50B+ parameter LLMs on consumer GPUs with RAM offloading at 4-6 tokens per second with 4-bit quantization or 2-3 tokens per second with 16-bit weights.

In human cognition theory, human thinking is governed by two systems: the fast and intuitive System 1 and the slower but more deliberative System 2. Recent studies have shown that incorporating System 2 process into Transformers including large language models (LLMs), significantly enhances their reasoning capabilities. Nevertheless, models that purely resemble System 2 thinking require substantially higher computational costs and are much slower to respond. To address this challenge, we present Dualformer, a single Transformer model that seamlessly integrates both the fast and slow reasoning modes. Dualformer is obtained by training on data with randomized reasoning traces, where different parts of the traces are dropped during training. The dropping strategies are specifically tailored according to the trace structure, analogous to analyzing our thinking process and creating shortcuts with patterns. At inference time, our model can be configured to output only the solutions (fast mode) or both the reasoning chain and the final solution (slow mode), or automatically decide which mode to engage (auto mode). In all cases, Dualformer outperforms the corresponding baseline models in both performance and computational efficiency: (1) in slow mode, Dualformer optimally solves unseen 30 x 30 maze navigation tasks 97.6% of the time, surpassing the Searchformer (trained on data with complete reasoning traces) baseline performance of 93.3%, while only using 45.5% fewer reasoning steps; (2) in fast mode, Dualformer completes those tasks with an 80% optimal rate, significantly outperforming the Solution-Only model (trained on solution-only data), which has an optimal rate of only 30%. For math problems, our techniques have also achieved improved performance with LLM fine-tuning, showing its generalization beyond task-specific models.

Inference-time techniques are emerging as highly effective tools to enhance large language model (LLM) capabilities. However, best practices for developing systems that combine these techniques remain underdeveloped due to our limited understanding of the utility of individual inference-time techniques and the interactions between them. Additionally, efficiently and automatically searching the space of model choices, inference-time techniques, and their compositions is challenging due to the large design space. To address these challenges, we introduce Archon, a modular framework for selecting, combining, and stacking layers of inference-time techniques to construct optimized LLM systems for target benchmarks. Rather than relying on a single LLM called once, we leverage a diverse set of LLMs and inference-time techniques, creating LLM systems greater than the sum of their parts. Archon defines an extensible design space, encompassing techniques such as generation ensembling, repeated sampling, ranking, fusion, critiquing, verification, and unit testing. It transforms the problem of building LLM systems into a hyperparameter optimization objective. Given the available LLMs, inference-time techniques, and compute budget, Archon utilizes hyperparameter search techniques to discover optimized architectures for target benchmark(s). We evaluate Archon architectures across a range of instruction-following, reasoning, and coding benchmarks, including MT-Bench, Arena-Hard-Auto, AlpacaEval 2.0, MixEval, MixEval Hard, MATH, and CodeContests. Archon architectures outperform frontier models, such as GPT-4o and Claude 3.5 Sonnet, on these benchmarks, achieving an average accuracy increase of 15.1 percentage points by using all available LLMs. We make our code and datasets available publicly on Github: https://github.com/ScalingIntelligence/Archon.

Historically, the pursuit of efficient inference has been one of the driving forces behind research into new deep learning architectures and building blocks. Some recent examples include: the squeeze-and-excitation module, depthwise separable convolutions in Xception, and the inverted bottleneck in MobileNet v2. Notably, in all of these cases, the resulting building blocks enabled not only higher efficiency, but also higher accuracy, and found wide adoption in the field. In this work, we further expand the arsenal of efficient building blocks for neural network architectures; but instead of combining standard primitives (such as convolution), we advocate for the replacement of these dense primitives with their sparse counterparts. While the idea of using sparsity to decrease the parameter count is not new, the conventional wisdom is that this reduction in theoretical FLOPs does not translate into real-world efficiency gains. We aim to correct this misconception by introducing a family of efficient sparse kernels for ARM and WebAssembly, which we open-source for the benefit of the community as part of the XNNPACK library. Equipped with our efficient implementation of sparse primitives, we show that sparse versions of MobileNet v1, MobileNet v2 and EfficientNet architectures substantially outperform strong dense baselines on the efficiency-accuracy curve. On Snapdragon 835 our sparse networks outperform their dense equivalents by 1.3-2.4times -- equivalent to approximately one entire generation of MobileNet-family improvement. We hope that our findings will facilitate wider adoption of sparsity as a tool for creating efficient and accurate deep learning architectures.

The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes the various methods of LLM Inference to provide a clear understanding of this domain. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques. This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems, such as why LLMs are memory-bound, how much memory and computation they need, and how to choose the right hardware. We systematically collate the latest advancements in efficient LLM inference, covering crucial areas such as model compression (e.g., Knowledge Distillation and Quantization), algorithm improvements (e.g., Early Exit and Mixture-of-Expert), and both hardware and system-level enhancements. Our survey stands out by analyzing these methods with roofline model, helping us understand their impact on memory access and computation. This distinctive approach not only showcases the current research landscape but also delivers valuable insights for practical implementation, positioning our work as an indispensable resource for researchers new to the field as well as for those seeking to deepen their understanding of efficient LLM deployment. The analyze tool, LLM-Viewer, is open-sourced.

Large Language Models (LLMs) have reshaped the landscape of artificial intelligence by demonstrating exceptional performance across various tasks. However, substantial computational requirements make their deployment challenging on devices with limited resources. Recently, compression methods using low-rank matrix techniques have shown promise, yet these often lead to degraded accuracy or introduce significant overhead in parameters and inference latency. This paper introduces Modular Decomposition (MoDeGPT), a novel structured compression framework that does not need recovery fine-tuning while resolving the above drawbacks. MoDeGPT partitions the Transformer block into modules comprised of matrix pairs and reduces the hidden dimensions via reconstructing the module-level outputs. MoDeGPT is developed based on a theoretical framework that utilizes three well-established matrix decomposition algorithms -- Nystr\"om approximation, CR decomposition, and SVD -- and applies them to our redefined transformer modules. Our comprehensive experiments show MoDeGPT, without backward propagation, matches or surpasses previous structured compression methods that rely on gradient information, and saves 98% of compute costs on compressing a 13B model. On Llama-2/3 and OPT models, MoDeGPT maintains 90-95% zero-shot performance with 25-30% compression rates. Moreover, the compression can be done on a single GPU within a few hours and increases the inference throughput by up to 46%.

To remove redundant components of large language models (LLMs) without incurring significant computational costs, this work focuses on single-shot pruning without a retraining phase. We simplify the pruning process for Transformer-based LLMs by identifying a depth-2 pruning structure that functions independently. Additionally, we propose two inference-aware pruning criteria derived from the optimization perspective of output approximation, which outperforms traditional training-aware metrics such as gradient and Hessian. We also introduce a two-step reconstruction technique to mitigate pruning errors without model retraining. Experimental results demonstrate that our approach significantly reduces computational costs and hardware requirements while maintaining superior performance across various datasets and models.

This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Efficient Training Scaling: A depth-growth paradigm that enables scaling from 1.6B to 4.8B parameters with significantly reduced computational resources, combined with a memory-efficient 8-bit optimizer. (2) Model Depth Pruning: A block importance analysis technique for efficient model compression to arbitrary sizes with minimal quality loss. (3) Inference-time Scaling: A repeated sampling strategy that trades computation for model capacity, enabling smaller models to match larger model quality at inference time. Through these strategies, SANA-1.5 achieves a text-image alignment score of 0.72 on GenEval, which can be further improved to 0.80 through inference scaling, establishing a new SoTA on GenEval benchmark. These innovations enable efficient model scaling across different compute budgets while maintaining high quality, making high-quality image generation more accessible.