Synchronizing local compiler cache.

.gitattributes

@@ -11920,3 +11920,50 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_6b32493175a70d9e16b9+747527b0/model.neff
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_6b32493175a70d9e16b9+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb50383f9a879a8375b9+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb50383f9a879a8375b9+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e70ec9049ca26a7f0f6+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_3360dfdbc9cf20ffe3ea+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_4be33b117e68e2de3326+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_4be33b117e68e2de3326+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e93fdf5154aebbd1ec7+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_73b50e8e61409e1f8fe1+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2547d4e8c084e5503d9+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2547d4e8c084e5503d9+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/transformer/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_daf3f26f1dd6b6a7b205/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/diffusion-transformer/PixArt-alpha/PixArt-XL-2-512x512/daf3f26f1dd6b6a7b205.json

@@ -0,0 +1,102 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "PixArt-alpha/PixArt-XL-2-512x512",
+  "_task": null,
+  "text_encoder": {
+    "architectures": [
+      "T5EncoderModel"
+    ],
+    "classifier_dropout": 0.0,
+    "d_ff": 10240,
+    "d_kv": 64,
+    "d_model": 4096,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "dropout_rate": 0.1,
+    "export_model_type": "t5-encoder",
+    "feed_forward_proj": "gated-gelu",
+    "initializer_factor": 1.0,
+    "is_encoder_decoder": false,
+    "is_gated_act": true,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": null,
+      "auto_cast_type": null,
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.21.18209.0+043b1bf7",
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": false,
+      "instance_type": "trn1",
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_sequence_length": 120,
+      "task": "feature-extraction",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 24,
+    "num_heads": 64,
+    "num_layers": 24,
+    "output_past": true,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "tie_word_embeddings": false,
+    "use_cache": false,
+    "vocab_size": 32128
+  },
+  "transformer": {
+    "_class_name": "PixArtTransformer2DModel",
+    "activation_fn": "gelu-approximate",
+    "attention_bias": true,
+    "attention_head_dim": 72,
+    "attention_type": "default",
+    "caption_channels": 4096,
+    "cross_attention_dim": 1152,
+    "double_self_attention": false,
+    "dropout": 0.0,
+    "in_channels": 4,
+    "interpolation_scale": null,
+    "neuron": {
+      "auto_cast": null,
+      "auto_cast_type": null,
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.21.18209.0+043b1bf7",
+      "dynamic_batch_size": false,
+      "float_dtype": "bf16",
+      "inline_weights_to_neff": false,
+      "instance_type": "trn1",
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_encoder_hidden_size": 4096,
+      "static_height": 64,
+      "static_num_channels": 4,
+      "static_sequence_length": 120,
+      "static_vae_scale_factor": 8,
+      "static_width": 64,
+      "task": "semantic-segmentation",
+      "tensor_parallel_size": 1
+    },
+    "norm_elementwise_affine": false,
+    "norm_eps": 1e-06,
+    "norm_num_groups": 32,
+    "norm_type": "ada_norm_single",
+    "num_attention_heads": 16,
+    "num_embeds_ada_norm": 1000,
+    "num_layers": 28,
+    "num_vector_embeds": null,
+    "only_cross_attention": false,
+    "out_channels": 8,
+    "output_attentions": false,
+    "patch_size": 2,
+    "upcast_attention": false,
+    "use_additional_conditions": null,
+    "use_linear_projection": false
+  }
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/2592b69b1afedac6c249.json

@@ -0,0 +1,58 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
+  "_task": "text-generation",
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 1.0,
+  "embedding_multiplier": 1.0,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "logits_scaling": 1.0,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
+    "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "float32",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "residual_multiplier": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 49152
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/f9479b3f424f0ae4542c.json

@@ -0,0 +1,62 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "llamafactory/tiny-random-Llama-3",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "float16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/43cfc61763bcaf55bb9e.json

@@ -0,0 +1,63 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/Llama-3.2-1B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": null,
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/a26633219d7308901cb9.json

@@ -0,0 +1,63 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/Llama-3.2-1B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": null,
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 5,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/ee0b934f9d86b0c0ec63.json

@@ -0,0 +1,63 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/Llama-3.2-1B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/eeb8b7f2495863c099b1.json

@@ -0,0 +1,63 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/Llama-3.2-1B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "float16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama4_text/tiny-random/llama-4/1ac5416e0e8a986447af.json

@@ -0,0 +1,81 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "tiny-random/llama-4",
+  "_task": "text-generation",
+  "attention_bias": false,
+  "attention_chunk_size": 128,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": 4,
+  "cache_implementation": "hybrid",
+  "floor_scale": 8192,
+  "for_llm_compressor": false,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 2,
+  "intermediate_size": 64,
+  "intermediate_size_mlp": 128,
+  "layer_types": [
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 1048576,
+  "model_type": "llama4_text",
+  "moe_layers": [
+    1,
+    3
+  ],
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "tiny-random/llama-4",
+    "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "no_rope_layers": [
+    1,
+    1,
+    1,
+    0
+  ],
+  "num_attention_heads": 1,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 1,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_qk_norm": true,
+  "vocab_size": 202048
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/68e8a9aa766528672764.json

@@ -0,0 +1,58 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "dacorvo/Mixtral-tiny",
+  "_task": "text-generation",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3584,
+  "max_position_embeddings": 1024,
+  "model_type": "mixtral",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "dacorvo/Mixtral-tiny",
+    "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "float16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 32000
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/microsoft/Phi-3-mini-4k-instruct/8d92c29cef19fddb825c.json

@@ -0,0 +1,62 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "microsoft/Phi-3-mini-4k-instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "embd_pdrop": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct",
+    "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 32064
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/yujiepan/phi-4-tiny-random/1d198d134b6736b8c253.json

@@ -0,0 +1,59 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "yujiepan/phi-4-tiny-random",
+  "_task": "text-generation",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {},
+  "embd_pdrop": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "yujiepan/phi-4-tiny-random",
+    "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "original_max_position_embeddings": 16384,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 100352
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/06d3a1f0282762f9f49a.json

@@ -0,0 +1,82 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 2,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 2,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/17b13a58612cc061dc5d.json

@@ -0,0 +1,82 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 2,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 2,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "float16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/239b5e7c2206baa8917a.json

@@ -0,0 +1,82 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "float32",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/a35f43930569fd7bd14c.json

@@ -0,0 +1,82 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "float16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/71aae2feb728a4bc1bea.json

@@ -0,0 +1,64 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 16,
+  "layer_types": [
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 1,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
+    "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/bda840f20094d5c6f760.json

@@ -0,0 +1,87 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen3-Embedding-0.6B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B",
+    "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 1,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 1
+  },
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/322124df0d79b4f7f8bb.json

@@ -0,0 +1,65 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 128,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 1,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 128,
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe",
+    "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "float32",
+    "tp_degree": 2
+  },
+  "norm_topk_prob": true,
+  "num_attention_heads": 2,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a97bb411dcd64871e1b1784620de52aab98fa041ae87f39fee46a8518b9f118
+size 78518

neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2282ddf8f23c97222ece601e4f0757f78fe73c6f641b3ffd4d3fe5c24e50b7
+size 287744

neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6bc663eeb8487a29b91741cdc21020abf78254b490d02397bdaaaaab3f2b119
+size 296094

neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61586b49e1e903cab9fff0482909f040c5e97621b59f6233899973b7cd27184d
+size 84807

neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33b221d4039eaaa99cb40b84d626d05299fe802098783ac5418f3b32574abe8
+size 646144

neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e70ec9049ca26a7f0f6+ed72d204/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e70ec9049ca26a7f0f6+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714ebfd9ca52e3b66ca85e6f7d1f920791921aa127dc18c9273251b90f276a77
+size 593552

neuronxcc-2.21.18209.0+043b1bf7/MODULE_0e70ec9049ca26a7f0f6+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad65458553f2e14df14309086b054374027fcf02dfa5d0c7e21b1977817f1ae
+size 3769344

neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20ed0858162f8fc2c58bc4c23d0925dbeda5897dae0889f87758206676394f4e
+size 81843

neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d9f3177230710833e1a22c473ceb0215149d4996fb169ded5f87e0ebd9b6e7
+size 246784

neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11296a74882475c7e044dddae990ac1e06a377d292f8bbbabccbf9f52a68de87
+size 255104

neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010699d8fe7fd543b752b93c8bc2cd72e5309050ab149427dfd589c97e7268c5
+size 81516

neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bf12c475e30b9ae5c3e55dc492a5b36e2b84326264d9707f19e411d4862c1a
+size 267264

neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c4af19c1f6118b30a135c4553925fc304a74428ae95971dcad784cdef2729b
+size 97794

neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3706159398be1c857cb9410baa841093252d4bd2db4a6ec6e5fcfcb5866e59d
+size 410624

neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d1111cccd29ce4edd640c6b5880fa7b920b5c1211396da06d3b58670ec7a12
+size 90382

neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07848927e2ef873e5477430034ef70cac7c7af77f9e216a81255e421762ed85
+size 359424

neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]