Synchronizing local compiler cache.

.gitattributes

@@ -6512,3 +6512,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/wrapped_nef
 neuronxcc-2.21.33363.0+82129205/MODULE_6a21c8e3eeb9125f1a9c+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_6a21c8e3eeb9125f1a9c+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_958d41f716f615f7fb01+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_81d6cd8b8dc031ee7a0b+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_9bf263b81ef3502ebaf1+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_9bf263b81ef3502ebaf1+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/97eac884cdfcaeb172fd.json

@@ -0,0 +1,81 @@
+{
+  "_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": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "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": 1024,
+    "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-2.21.33363.0+82129205/MODULE_81d6cd8b8dc031ee7a0b+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_81d6cd8b8dc031ee7a0b+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6ebb56349b00507373969973419d2756d9d5d9a00fd5a4d3aa6e81359ea1bd
+size 532500

neuronxcc-2.21.33363.0+82129205/MODULE_81d6cd8b8dc031ee7a0b+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b0069fa1bd690cf300e267b07487a916946714bad333f789004f6de68b1fa9
+size 1813504

neuronxcc-2.21.33363.0+82129205/MODULE_9bf263b81ef3502ebaf1+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_9bf263b81ef3502ebaf1+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:072ccb9fb7d86290e26a5375603e1afb662e5f281437419f3893421c85ff7bf3
+size 555200

neuronxcc-2.21.33363.0+82129205/MODULE_9bf263b81ef3502ebaf1+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abfcce82a549ba196006301f204ea97fa503fdd16304c712b6b4deddf0afcd2
+size 1025024

neuronxcc-2.21.33363.0+82129205/MODULE_9bf263b81ef3502ebaf1+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea56c1a6ce9ca0430746e1682840951d360bc6c049ba67b86f476be65554f9b2
+size 1147413