Synchronizing local compiler cache.

.gitattributes

@@ -6482,3 +6482,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_3d866856ba460ee705b0+0c2bddb9/wrapped_nef
 neuronxcc-2.21.33363.0+82129205/MODULE_cc1db43e7c7ab058977c+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_cc1db43e7c7ab058977c+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_f36c747011966d6fae74+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_2b451d8e48f4d44d430c+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_2b451d8e48f4d44d430c+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_8db3d26dbdcf38e6350a+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/gemma3_text/google/gemma-3-270m-it/c5893ac2150961103e95.json

@@ -0,0 +1,80 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "google/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": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "google/gemma-3-270m-it",
+    "checkpoint_revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 4,
+    "max_batch_size": 4,
+    "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": "0.4.5.dev2",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn2",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 4
+  },
+  "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,
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

neuronxcc-2.21.33363.0+82129205/MODULE_2b451d8e48f4d44d430c+ac10809c/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/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_2b451d8e48f4d44d430c+ac10809c/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa00f555d2609936a609bb82e8b3791f284f3c4f9f5cad412211e5d627e4d22
+size 2641803

neuronxcc-2.21.33363.0+82129205/MODULE_2b451d8e48f4d44d430c+ac10809c/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732cf57c21041df7121a5520826feaa621018535e17f1ad2d0b5cedfe122dfb7
+size 2520064

neuronxcc-2.21.33363.0+82129205/MODULE_2b451d8e48f4d44d430c+ac10809c/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049580c8bd4f9a0858fc4b6cb617739523c0a112ab38c0cfdc1fdd9ccb55197f
+size 2642335

neuronxcc-2.21.33363.0+82129205/MODULE_8db3d26dbdcf38e6350a+a32116a7/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/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.33363.0+82129205/MODULE_8db3d26dbdcf38e6350a+a32116a7/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d64742b7d45855c3d77c42a1b22c3d44204e1f9a9f39cf78d1dbf294da74450
+size 1742062

neuronxcc-2.21.33363.0+82129205/MODULE_8db3d26dbdcf38e6350a+a32116a7/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a844153868c8935d0be8b980f26f5415655bc73dbe7387d21cc7e04646b65617
+size 6319104