Synchronizing local compiler cache.

.gitattributes

@@ -6506,3 +6506,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_a155b32467ad91efdb56+a02c3a36/wrapped_nef
 neuronxcc-2.21.33363.0+82129205/MODULE_e45e2c512692918b8ac7+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_c96e8a76473cbbe30609+bf3a5a22/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_d130c645df160dbdf55c+bf3a5a22/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/9fe76ed73880dddfee60.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": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "google/gemma-3-270m-it",
+    "checkpoint_revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3",
+    "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": "2.21.33363.0+82129205",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.5.dev2",
+    "output_logits": false,
+    "pp_degree": 1,
+    "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,
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/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/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9784d05730e15de6d1cf1791873840a6995583c3a7a29e3ac5701802fd609f3
+size 528187

neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0aa634225715ea311d2426849ec89cacfb2b66322132c6ea28fd4c31f147fd
+size 18791424

neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/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/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc9980209b96c5b9cd842953a264275b22adf233db39cfa566822522b055584
+size 566028

neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825f66ab479df997684b11bc5daa0483fe77f5339218f7ce56b1c565675173a2
+size 1403904

neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab174cb8fed788f1db993fc19c839f1f13fbdf5fff9b75fdee57da5ab44a560
+size 1526293