Synchronizing local compiler cache.

.gitattributes

@@ -3884,3 +3884,7 @@ neuronxcc-2.20.9961.0+0acef03a/MODULE_38415f1a88551d65c8cb+ed72d204/model.neff f
 neuronxcc-2.20.9961.0+0acef03a/MODULE_c839c3566b4b3f8ea4d7+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.20.9961.0+0acef03a/MODULE_c839c3566b4b3f8ea4d7+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.20.9961.0+0acef03a/MODULE_cb6febf0237e8ba1d4a2+ae6a382b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_49a4358be1d6418e0dab+ae6a382b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_aeff7c58d06fb4c123fc+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_fdd3c2470676e1b82f01+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.20.9961.0+0acef03a/0_REGISTRY/0.3.1.dev0/qwen3/Qwen/Qwen3-0.6B/1dec833208e4948af7a0.json

@@ -0,0 +1,72 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen3-0.6B",
+  "_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,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 4,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "Qwen/Qwen3-0.6B",
+    "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.20.9961.0+0acef03a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.3.1.dev0",
+    "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": 2,
+    "vocab_parallel": false
+  },
+  "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": 151936
+}

neuronxcc-2.20.9961.0+0acef03a/MODULE_49a4358be1d6418e0dab+ae6a382b/compile_flags.json

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

neuronxcc-2.20.9961.0+0acef03a/MODULE_49a4358be1d6418e0dab+ae6a382b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abdf4d53539b2ab9ae9b1290c72f0bfa819e9b3d8eeefb52a0037f443f5bb474
+size 132615

neuronxcc-2.20.9961.0+0acef03a/MODULE_49a4358be1d6418e0dab+ae6a382b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717f587c7b9649dc3e484095e3c97adac681ee5958f89b6fea59dfd6e534407e
+size 492544

neuronxcc-2.20.9961.0+0acef03a/MODULE_aeff7c58d06fb4c123fc+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-2.20.9961.0+0acef03a/MODULE_aeff7c58d06fb4c123fc+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf1703e47c67246e6b22fd05bad4628456000316fb056e4e1df7a9851ad8857
+size 848672

neuronxcc-2.20.9961.0+0acef03a/MODULE_aeff7c58d06fb4c123fc+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c937a59786c26933331fedde7a83358c278e549043bdbff807d738f8d6f1ec74
+size 27546624

neuronxcc-2.20.9961.0+0acef03a/MODULE_fdd3c2470676e1b82f01+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-2.20.9961.0+0acef03a/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d0640d765132bd086a33e99d182e5d9a8aac851a83138e176a97317ed251aa
+size 702501

neuronxcc-2.20.9961.0+0acef03a/MODULE_fdd3c2470676e1b82f01+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d20473d5130015c4ed7785e89f4542d36de9f1cdf305b64fcda5c9247aa10a31
+size 2612224

neuronxcc-2.20.9961.0+0acef03a/MODULE_fdd3c2470676e1b82f01+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a74f0000a9cffcaeef9a6c12656c7f1f35aab38f4a71c957b4264ad0f9c4e03
+size 2742657