Synchronizing local compiler cache.

.gitattributes

@@ -9919,3 +9919,7 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_314f165410084295ebb3+431f5505/model.neff f
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_88c93ecb8ca704ef50ed+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_da903d9dca58ebfe4a37+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_da903d9dca58ebfe4a37+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_054cfe09cdfc1f32d0d3+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_3c71a838fcbfa1bfff33+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_6104e0178f4c97e10ec1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_6104e0178f4c97e10ec1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen3/Qwen/Qwen3-32B/2439c6fa321a6669c02c.json

@@ -0,0 +1,72 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen3-32B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "Qwen/Qwen3-32B",
+    "checkpoint_revision": "d47b0d4ae4b48fde975756bf360a63a9cca8d470",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 8,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.19.8089.0+8ab9f450",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0.dev5",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 4096,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 8,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_054cfe09cdfc1f32d0d3+431f5505/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.19.8089.0+8ab9f450/MODULE_054cfe09cdfc1f32d0d3+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:171e725d36546f1dbd4fccf14156343597030574a3b4a73389a5f47a739d9d9b
+size 298017

neuronxcc-2.19.8089.0+8ab9f450/MODULE_054cfe09cdfc1f32d0d3+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe82d6736ce67ec4e09d45f1131e270dd36336e5058ae5bafe8d111b6777a08
+size 7476224

neuronxcc-2.19.8089.0+8ab9f450/MODULE_3c71a838fcbfa1bfff33+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-2.19.8089.0+8ab9f450/MODULE_3c71a838fcbfa1bfff33+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfcd75f2800a4f1b262ac0510fc2a8fb3ba38565c469a6505fb81cf93d1717f
+size 1818311

neuronxcc-2.19.8089.0+8ab9f450/MODULE_3c71a838fcbfa1bfff33+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f9eecd3c2adaedf0748a081d2250e4a8ec0b9afe6929c8187b8f0c25984d76
+size 4731904

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6104e0178f4c97e10ec1+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-2.19.8089.0+8ab9f450/MODULE_6104e0178f4c97e10ec1+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77de5dd5486840f2fdd2f04d117eb95810c719f5f6bf10329b86f9676ba7a50e
+size 1624253

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6104e0178f4c97e10ec1+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb873cff13d1be16b2ace66a9482249e791283d8da31d95dfd644799832e555
+size 6790144

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6104e0178f4c97e10ec1+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:527c37901f6ee7e34216247f7be1ccfe5356f16f0ada36f53b093e6264155fc1
+size 7084118