Synchronizing local compiler cache.

.gitattributes

@@ -7882,3 +7882,8 @@ neuronxcc-2.21.33363.0+82129205/MODULE_d6713fbd83cd891615f3+a02c3a36/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_d6713fbd83cd891615f3+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_f90d09e1438492736d3c+c4f887dc/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_f90d09e1438492736d3c+c4f887dc/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_213ad9728f93ce707ff0+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_866615121c80b108f18d+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+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+82129205/0_REGISTRY/0.4.6.dev4/f2b3698075778373c8db941c7e90213b3c7a6dc311947938cb2ff93518c6a4cc/1f8dd49c1101a3bcbfaf.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": "8e5127a746b5297bc637a347f6279cb34a0d1d9d",
+    "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": 32,
+    "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+82129205/0_REGISTRY/0.4.6.dev4/gemma3/tengomucho/tiny-random-gemma-3-vlm/1f8dd49c1101a3bcbfaf.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": "8e5127a746b5297bc637a347f6279cb34a0d1d9d",
+    "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": 32,
+    "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_213ad9728f93ce707ff0+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_213ad9728f93ce707ff0+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5883954151d2373de4a87a2f5b2a08a670d791c6f5878fc43922d2793441a8
+size 107163

neuronxcc-2.21.33363.0+82129205/MODULE_213ad9728f93ce707ff0+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a007596edd2bf3db665fb3c2069b7b17c8be6f389d909cf1265b788f36f242
+size 656384

neuronxcc-2.21.33363.0+82129205/MODULE_866615121c80b108f18d+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_866615121c80b108f18d+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf4efeb25a6e5d4498a29635f2085805945ac8ece5c20c9ca11cbf069e5bdab
+size 109574

neuronxcc-2.21.33363.0+82129205/MODULE_866615121c80b108f18d+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb6767aa8d9fd31cb4b37d6d5537d4f0b6479db57c2c0ac3948bb333de0ad8b
+size 492544

neuronxcc-2.21.33363.0+82129205/MODULE_866615121c80b108f18d+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555d930b5be5aea79dc8de0cf09ce8313735cc090e10767cd011044dbf009dbf
+size 501283

neuronxcc-2.21.33363.0+82129205/MODULE_9b7eb59becdba58feaf4+c4f887dc/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/vision_encoder/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_9b7eb59becdba58feaf4+c4f887dc/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2108c8bdd21eebffc5de6069d4e84357115456e3ee3973c9d35fade13918c6
+size 42192

neuronxcc-2.21.33363.0+82129205/MODULE_9b7eb59becdba58feaf4+c4f887dc/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faad9069616a57d672efb6f47a004ba83bf4a0d7117841138f6ed411f5e4e35c
+size 4393984

neuronxcc-2.21.33363.0+82129205/MODULE_9b7eb59becdba58feaf4+c4f887dc/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd88017bbd2dc4353559e502f3afb74d769e830411c2662fbb0aec5ca5326d31
+size 4404834