Synchronizing local compiler cache.

.gitattributes

@@ -11698,3 +11698,9 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_95840175439e51d09ab5+ed72d204/model.neff
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_88d939fd44369b345588+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_a7fc835e8d2d4a651ceb+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_a7fc835e8d2d4a651ceb+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_244fefb64e90dc362ba3+564b7b5b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_57a70f49b1263b4a4dcf+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_57a70f49b1263b4a4dcf+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_782b8be7c92212bda95b+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_c89c12572a6072d99c3d+d0d57c8a/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_c89c12572a6072d99c3d+d0d57c8a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen3_moe/Qwen/Qwen3-Coder-480B-A35B-Instruct/130cb034c34440c28a06.json

@@ -0,0 +1,68 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 62,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 2560,
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
+    "checkpoint_revision": "9d90cf8fca1bf7b7acca42d3fc9ae694a2194069",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 64,
+    "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": "0.4.0.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn2",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 64
+  },
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts": 160,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "qkv_bias": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.0,
+  "shared_expert_intermediate_size": 0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_qk_norm": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_244fefb64e90dc362ba3+564b7b5b/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/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_244fefb64e90dc362ba3+564b7b5b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f0ab146574db8611f422e96ef1b076d653059d2209a8bc272ff8966fb168de
+size 16167103

neuronxcc-2.21.18209.0+043b1bf7/MODULE_244fefb64e90dc362ba3+564b7b5b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95384571d794167344887830f23971de027e3eceda04a138da8c50fcc421f1d2
+size 157973504

neuronxcc-2.21.18209.0+043b1bf7/MODULE_57a70f49b1263b4a4dcf+747527b0/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_57a70f49b1263b4a4dcf+747527b0/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e50d8dce9cb76b0e61a53054008beb3d248e3a944522df64d52b5a7a820d61ba
+size 2531606

neuronxcc-2.21.18209.0+043b1bf7/MODULE_57a70f49b1263b4a4dcf+747527b0/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47a95ffe4c8d4343f5df0cf877b08d3a788fa273fb27e56495331666015bd91
+size 4547584

neuronxcc-2.21.18209.0+043b1bf7/MODULE_57a70f49b1263b4a4dcf+747527b0/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1b4d243acbbfc4db6079d3f3970ea85d9537e4a13ff3673acbd6b747439e68
+size 4622595

neuronxcc-2.21.18209.0+043b1bf7/MODULE_782b8be7c92212bda95b+877608f3/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_782b8be7c92212bda95b+877608f3/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dbca1c08c0f6ca72415246c162123dcb7c209f33a8ac6815b5ae92c4d61877e
+size 1772495

neuronxcc-2.21.18209.0+043b1bf7/MODULE_782b8be7c92212bda95b+877608f3/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ed35fe5169a3b03a7c9ca5ba748976231b2d9de54990ac4eec2472a6d3ec66
+size 34612224

neuronxcc-2.21.18209.0+043b1bf7/MODULE_c89c12572a6072d99c3d+d0d57c8a/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/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_c89c12572a6072d99c3d+d0d57c8a/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b624c7f1bcb96b1caf66e497f658d8423c1c6d6350f206aa0f7d8af9d0f45dd7
+size 3289230

neuronxcc-2.21.18209.0+043b1bf7/MODULE_c89c12572a6072d99c3d+d0d57c8a/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6112463a00a96d79496f6bd59463db1c4971405ab151a3cf5cc66627bedf98ec
+size 5796864

neuronxcc-2.21.18209.0+043b1bf7/MODULE_c89c12572a6072d99c3d+d0d57c8a/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4414b98bfc82077569950fce6a03e2176a4e9088e98426e724ee40bc44641a6d
+size 6177677