Synchronizing local compiler cache.

.gitattributes

@@ -7313,3 +7313,6 @@ neuronxcc-2.23.6484.0+3b612583/MODULE_8648a6d0cbd639733a91+12dd9119/model.neff f
 neuronxcc-2.23.6484.0+3b612583/MODULE_8e357b01248f3533a916+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.23.6484.0+3b612583/MODULE_bbb5c437605f618838ec+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.23.6484.0+3b612583/MODULE_bbb5c437605f618838ec+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_a9e06ac679b7a05c239b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_b85127c63c8b6628b99b+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_b85127c63c8b6628b99b+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/86b3f44f9c03e243bbe9.json

@@ -0,0 +1,82 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/gemma-3-270m-it",
+  "_sliding_window_pattern": 6,
+  "_task": "text-generation",
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "dtype": "bfloat16",
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "unsloth/gemma-3-270m-it",
+    "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 8192,
+    "max_topk": 256,
+    "n_active_tokens": 8192,
+    "neuronxcc_version": "2.23.6484.0+3b612583",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.6.dev3",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 0,
+    "sequence_length": 8192,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "unsloth_fixed": true,
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

neuronxcc-2.23.6484.0+3b612583/MODULE_a9e06ac679b7a05c239b+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.23.6484.0+3b612583/MODULE_a9e06ac679b7a05c239b+519f203d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918fa50b32a9f8bf802d781b15c1bdd771ef45c083ab10a9bb731c1e9ebaa3c6
+size 2749032

neuronxcc-2.23.6484.0+3b612583/MODULE_a9e06ac679b7a05c239b+519f203d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9fc51ecbcb0e33214fe60387316147efd7b28b569fe42d6a1866fa56810fb0a
+size 6257664

neuronxcc-2.23.6484.0+3b612583/MODULE_b85127c63c8b6628b99b+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.23.6484.0+3b612583/MODULE_b85127c63c8b6628b99b+84337dd9/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dfc33ac5b4ff6f40e4b327917600bc43cfd1d1838a91cfa2102f5436f655d0
+size 1805904

neuronxcc-2.23.6484.0+3b612583/MODULE_b85127c63c8b6628b99b+84337dd9/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e4efcf6906c79ca4ff634471d273095e09070c35d12ab359939e178423eb7a
+size 1649664

neuronxcc-2.23.6484.0+3b612583/MODULE_b85127c63c8b6628b99b+84337dd9/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80a0d8945dc1b46fb3a2101a5a57bc25d45970b9691b536757bb919175852836
+size 1772053