Synchronizing local compiler cache.

.gitattributes

@@ -17344,3 +17344,4 @@ neuronxcc-2.21.33363.0+82129205/MODULE_5477abf66ec2ad45634f+ab1d9fc5/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_edd5e29803b3ef9744ce+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_e0f85f7aad2e7ef41614+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_d62199f953508b202218+ab1d9fc5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_089c4916448376960f90+ab1d9fc5/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/b5da5b563a8f13eeeffbd5285cafbeb09a7c6b9a12376b388e616d180fdb84f9/1054b1e4c31afceb875d.json

@@ -0,0 +1,66 @@
+{
+  "_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,
+  "dtype": "bfloat16",
+  "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": 16,
+    "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": 4,
+    "max_batch_size": 16,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.33363.0+82129205",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.6.dev3",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 1024,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn2",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 4
+  },
+  "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-2.21.33363.0+82129205/MODULE_089c4916448376960f90+ab1d9fc5/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.33363.0+82129205/MODULE_089c4916448376960f90+ab1d9fc5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d827568b26f7bd1503efeb6403e9a628e36265225eac9ebe61952c982bf8d1ae
+size 10008480

neuronxcc-2.21.33363.0+82129205/MODULE_089c4916448376960f90+ab1d9fc5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0f577277548c838d7d5861fe2cb993b3e855964193a686edf9f2158a43aa0b
+size 5633024