Synchronizing local compiler cache.

.gitattributes

@@ -16552,3 +16552,34 @@ neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_eea79ad4b5b63ff68d1f+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_fffa4c481b28ac601395+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_fffa4c481b28ac601395+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/wrapped_neff.hlo 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_975648b1780210c41a55+7f755e5c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/wrapped_neff.hlo 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/MODULE_d6db01106f253fc7b776+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/4409b94110a511ee8fae.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": 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,
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

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+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/ca8ebd0dd1c56ed002d7.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": 2,
+    "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": "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+82129205/0_REGISTRY/0.4.5.dev2/gemma3_text/google/gemma-3-270m-it/4409b94110a511ee8fae.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": 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,
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_5f9966e0-514d-4e13-9b7a-a5fb0c27cca1/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab14f002e51d52ed01d96ec7833c4ff77cf28108c4b0f1ba5a4256cec871f44
+size 20055

neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6647ec86502f59d4bc9f91c30f9636297a00c9be517842831ead2450e7cf442d
+size 144384

neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e907335ca7cbeeb116e37b6d9efc9af29613ab3b5936de32e5e62393ffd7b1
+size 152103

neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+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_1af22ef97be0fe871938+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde78f832bf7b42825123a2072be02643a57f95cbd882555ecd842f6d6419934
+size 708855

neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af5db1b519fd304a769ec6c3571b8730b8f69c2c047ab2289f4d15a66c87fac
+size 7660544

neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+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_1b5fd23da565a2f62ae1+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a0120595235859cb5d3b5081228df5cee5f5b7509e5089c2e0b6a2ffdf54cb
+size 692215

neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4df5bdd88883f7b8592e7ad15fc56ac4677efbdae065aa8106d8df7484bbc69
+size 1045504

neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3948819097df7a66219c39985f00a04157938ea56636a068d74f644e3d7b6e06
+size 1167896

neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+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_2c2347b5dccbe5eb00d1+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9f88a7adc91f3c99012a220709f8d0099fa64358b63acd3f16030322f1b134
+size 669533

neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b6d32fe855702ba97203b0c9eb3a5446060950a269f4450c8b6eb507786e37
+size 1813504

neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+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_38fd7ae3ba23ea0fba3d+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318ff99081c83cf153684d419f67e6f92b73c74b6486c0937dd877e49e4ba542
+size 699082

neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c57ec40f5bbf770e15df1c247db392d419051dd35f6c932e3a93a53660b266a2
+size 1793024

neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ede6c5cd85357ee4cf8009b98d60f7f17ec70de0f5c9849dee7d32abd7787b
+size 1915416

neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_c8fa8278-d095-4975-a132-7e34528bc463/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e145d2c1f69646ad6185ccf2ab6e40e023d18c98298a31281afd17759228cf3a
+size 15907

neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876560c847b0b4e90d582baa69d7ad73538ffeb9ca7b8d9fb428b43246c64106
+size 707584

neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f876494d415ba816ca2bb7f9de1c8229c9ba01c1a84dc3088e695d256480a142
+size 711550

neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_7534cf8c-b224-45c6-86c0-f01d9c3944eb/compiler_workdir/NeuronGemma3MLP/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b17a7309352127aaa945d8632b425c2deb5a5e784ed4854193113d3bd8643540
+size 1958

neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_596a05a6-131d-4f52-97c2-1218c98883ab/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2ec47100914dfc3fc8af9739d73eed6a06058f4c6df424749e311f572d2694
+size 18364

neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9bcce5c2a75346e991e7f0d20ffdcf7f640bca02839aafd0a79515ed0a7fc3a
+size 144384

neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68d9a7fd5893c67ddc82df8fca7fe60cdb5a743cc375c85f3dbf35c028b331f
+size 152103

neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+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_614f928fe1aae4555d06+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29cad13786fa765386b03c15c001f2f1904fa92081c3f6ac9686359bef4d80e
+size 567509

neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5d03aba2c6bd35518ce07e85fbdb17e8492d8fe1f20d39548af8d20603a850
+size 7158784

neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_ae6488d1-6ee8-4dc6-89dc-051226392a26/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]