Synchronizing local compiler cache.

.gitattributes

@@ -12465,3 +12465,6 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_f79242fa2cd3c81c8c0a+24129607/model.neff
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_02da4d2e49c714037de9+283df001/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_b855b09b596a4ebc0859+2dde74c7/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_b855b09b596a4ebc0859+2dde74c7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_58aeb300deafebd2c10b+283df001/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_db92fcb3052ae67b1e5b+2dde74c7/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_db92fcb3052ae67b1e5b+2dde74c7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/Qwen/Qwen3-30B-A3B-Instruct-2507/6d99a8844ea19051694a.json

@@ -0,0 +1,64 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 8,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
+    "checkpoint_revision": "0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 16,
+    "max_batch_size": 8,
+    "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": 16
+  },
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_58aeb300deafebd2c10b+283df001/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/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_58aeb300deafebd2c10b+283df001/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a85901e485ebd4ae0fb359e446cfe207f62d455ced1cd351dfb984dcb3b3b53
+size 9719549

neuronxcc-2.21.18209.0+043b1bf7/MODULE_58aeb300deafebd2c10b+283df001/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a88b2f9547988049c3eca6983dc6b43feaa6812247f75fff2b7db8fa6716063
+size 37592064

neuronxcc-2.21.18209.0+043b1bf7/MODULE_db92fcb3052ae67b1e5b+2dde74c7/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/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_db92fcb3052ae67b1e5b+2dde74c7/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa3e07eb9e999127fa5275ac461bb1ab8ebe7ea657bab793adef98cb91d02ab
+size 3782411

neuronxcc-2.21.18209.0+043b1bf7/MODULE_db92fcb3052ae67b1e5b+2dde74c7/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a564aa57b11c905e232c75d6e38c308f0fe79feac6b0eeb1a8f61efc408450c4
+size 7937024

neuronxcc-2.21.18209.0+043b1bf7/MODULE_db92fcb3052ae67b1e5b+2dde74c7/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecbdbedd0e85c64c19341f5ed41612d71a1292c65f9afe6fdd375948e84ad1d
+size 8206229