Synchronizing local compiler cache.

.gitattributes

@@ -7887,3 +7887,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_866615121c80b108f18d+a02c3a36/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_866615121c80b108f18d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_9b7eb59becdba58feaf4+c4f887dc/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_9b7eb59becdba58feaf4+c4f887dc/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_531086d2d1e6a2d23ebd+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_d962f9089341da526ccb+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_d962f9089341da526ccb+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev4/179f57339300218ee5f1e16199abfeaede9aa891026ff77f3e8e13d9e193a48f/f6c4e510f62a9f40e4d4.json

@@ -0,0 +1,97 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "tengomucho/tiny-random-gemma-3-vlm",
+  "_task": "image-text-to-text",
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "dtype": "bfloat16",
+  "eoi_token_index": 256000,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "neuron": {
+    "_serialized_key": "NxDVLMNeuronConfig",
+    "batch_size": 2,
+    "capacity_factor": null,
+    "checkpoint_id": "tengomucho/tiny-random-gemma-3-vlm",
+    "checkpoint_revision": "fbd846052676e5f7b417d7df6a736f5e980106b2",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "image_seq_len": 256,
+    "image_size": 896,
+    "local_ranks_size": 2,
+    "max_batch_size": 2,
+    "max_context_length": 2048,
+    "max_num_images": 5,
+    "max_topk": 256,
+    "n_active_tokens": 2048,
+    "neuronxcc_version": "2.21.33363.0+82129205",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.6.dev4",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 0,
+    "sequence_length": 2048,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_key_value_heads": 2,
+  "text_config": {
+    "_sliding_window_pattern": 2,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "dtype": "bfloat16",
+    "final_logit_softcapping": null,
+    "head_dim": 128,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 128,
+    "layer_types": [
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 1,
+    "query_pre_attn_scalar": 168,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 2,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 32,
+    "image_size": 896,
+    "intermediate_size": 128,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 2,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

neuronxcc-2.21.33363.0+82129205/MODULE_531086d2d1e6a2d23ebd+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_531086d2d1e6a2d23ebd+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8baa176ec99ed6ce0bb68762bbecc359e01625a863f906c412f6b8d841027ab
+size 107907

neuronxcc-2.21.33363.0+82129205/MODULE_531086d2d1e6a2d23ebd+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b8d43032515b5f9fe0f8db8a937a2ec88788bb9a1121e92ac2e8afe86958e3
+size 635904

neuronxcc-2.21.33363.0+82129205/MODULE_d962f9089341da526ccb+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_d962f9089341da526ccb+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a76380f0d5727cafffe24033789a75885fe19f2cc182fe426098b202b12512
+size 110370

neuronxcc-2.21.33363.0+82129205/MODULE_d962f9089341da526ccb+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d84284794f25240dc9295cd82502bcdf43304e60a30774caf13173318c3a03f
+size 482304

neuronxcc-2.21.33363.0+82129205/MODULE_d962f9089341da526ccb+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54a31372e905a4325cdb4be32a5b2915d795a60fa91e421906598d0ea9059dd
+size 491105