Synchronizing local compiler cache.

.gitattributes

@@ -15158,3 +15158,17 @@ neuronxcc-2.21.33363.0+82129205/MODULE_a22c65ba0c6c7a55032b+692b3dff/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_a22c65ba0c6c7a55032b+692b3dff/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_dac939ac0fb756b0c5a0+8669224f/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_dac939ac0fb756b0c5a0+8669224f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_0c0c570336081d2ddd3c+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_1ac352f09de58a202958+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_3127262d3bc119879dfa+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_85454497bce26576d95d+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_85454497bce26576d95d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_9088cab965c880f237a4+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_9088cab965c880f237a4+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_a7db8b94be5fa8c63086+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_cafaaccbcb3304f08d70+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_da1fe9f94d1912f89f98+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_e423e95ee77bbcfd6982+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_e423e95ee77bbcfd6982+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_fa675f3a434a3d346112+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_fa675f3a434a3d346112+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/88837b9b04ca62ade2e5.json

@@ -0,0 +1,62 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-3.1-8B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct",
+    "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.33363.0+82129205",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.4.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": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.2-1B-Instruct/184d3988bab3b0aea22a.json

@@ -0,0 +1,62 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-3.2-1B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "9213176726f574b556790deb65791e0c5aa438b6",
+    "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": false,
+    "optimum_neuron_version": "0.4.4.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": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.2-1B-Instruct/1aff29ca40a5d84dc158.json

@@ -0,0 +1,63 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-3.2-1B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "9213176726f574b556790deb65791e0c5aa438b6",
+    "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": false,
+    "optimum_neuron_version": "0.4.4.dev2",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 8192,
+    "sequence_parallel_enabled": true,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.33363.0+82129205/MODULE_0c0c570336081d2ddd3c+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_0c0c570336081d2ddd3c+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f928de65496854001ada7e5e53a70b74032c92d33e8c48710fb591fb579ccc
+size 434848

neuronxcc-2.21.33363.0+82129205/MODULE_0c0c570336081d2ddd3c+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8c21ed45fb889dd1b85413d67e9ff34d25354073330931cc7bceb2f401e862
+size 114985984

neuronxcc-2.21.33363.0+82129205/MODULE_1ac352f09de58a202958+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_1ac352f09de58a202958+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0a59f05f75f44d4f152165dd1498bbacd1bb716a5038c4edefa78073442b0c
+size 928451

neuronxcc-2.21.33363.0+82129205/MODULE_1ac352f09de58a202958+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576906166482527d7ac353da0534e8fe32fa597ef3ab1f5c105a0538e3da863a
+size 41851904

neuronxcc-2.21.33363.0+82129205/MODULE_3127262d3bc119879dfa+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_3127262d3bc119879dfa+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2d78445e08d3210569f8562c247dacd71c96303252860c4275cd1aa5223c24
+size 465940

neuronxcc-2.21.33363.0+82129205/MODULE_3127262d3bc119879dfa+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf958b8008d117987b44745851fca69111ec2ac1ab25578a16fed03f2580b530
+size 114279424

neuronxcc-2.21.33363.0+82129205/MODULE_85454497bce26576d95d+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_85454497bce26576d95d+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2941ff5bfa2ac33683363d48b44dd5eb9a7930bd31fdea40bf832b3cadc2e25
+size 769257

neuronxcc-2.21.33363.0+82129205/MODULE_85454497bce26576d95d+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7f6ea5e68057a9d5ad76e682963091a6503e49155f4c601cbd9c31a835d58c
+size 8899584

neuronxcc-2.21.33363.0+82129205/MODULE_85454497bce26576d95d+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3692add274fc47e40761a3044d5e14815585874653cfb04fcb9a420478d78c18
+size 9047399

neuronxcc-2.21.33363.0+82129205/MODULE_9088cab965c880f237a4+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_9088cab965c880f237a4+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f3742f0d123d956d174e40c072a858a13a03ef258da8f2056da95bbed4653ab
+size 756502

neuronxcc-2.21.33363.0+82129205/MODULE_9088cab965c880f237a4+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a2b18be62bf42c74fa32c3167d04500cd5dcf04213099083be59e17ef89ee8
+size 6902784

neuronxcc-2.21.33363.0+82129205/MODULE_9088cab965c880f237a4+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa0f993403352abd4aad1c6397c69b3cb2599e47624d4b32fa8fa0c3e2f4560
+size 7050133

neuronxcc-2.21.33363.0+82129205/MODULE_a7db8b94be5fa8c63086+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_a7db8b94be5fa8c63086+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff7812e7179908192c31870402bb39536413f49103f4d67f6d7f204f3e5185f
+size 972333

neuronxcc-2.21.33363.0+82129205/MODULE_a7db8b94be5fa8c63086+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c7cfabffc71aff561f9f1a1a4f12dbbe2c485599f7f1c0c901469bef84860d
+size 41892864

neuronxcc-2.21.33363.0+82129205/MODULE_cafaaccbcb3304f08d70+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_cafaaccbcb3304f08d70+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a75d6679d5de1f5062dfddb72d5621e645bc2830fdb1b70c65529e581d9cd0
+size 505502

neuronxcc-2.21.33363.0+82129205/MODULE_cafaaccbcb3304f08d70+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549f16d4c19caabedc4e743121854d85ce13e58b9deed7463efd5706da06c9e7
+size 114074624

neuronxcc-2.21.33363.0+82129205/MODULE_da1fe9f94d1912f89f98+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_da1fe9f94d1912f89f98+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1239ef1590682b574cd985d60ca0602fb970b86e4a717dc3a70cb4afaaabb860
+size 869444

neuronxcc-2.21.33363.0+82129205/MODULE_da1fe9f94d1912f89f98+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1872dff540e41af1855780dc910589f7bfcdf22983d14413e19ffcc5ca6e963f
+size 6616064

neuronxcc-2.21.33363.0+82129205/MODULE_e423e95ee77bbcfd6982+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_e423e95ee77bbcfd6982+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3e756d8fcdf483ac9d147d0dd0a09ec65b64b3e8fd6380879fb2315321d65d
+size 395607

neuronxcc-2.21.33363.0+82129205/MODULE_e423e95ee77bbcfd6982+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62664749edfececd6069d80c0fdb784d83afb1bb3838d22a7a6a7a429144b4db
+size 2171904

neuronxcc-2.21.33363.0+82129205/MODULE_e423e95ee77bbcfd6982+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63cf62f2c48a4f9cde1e8da4213d91c7a2fe5f7debbf1d62ee79f1ebc70a3c66
+size 2245876

neuronxcc-2.21.33363.0+82129205/MODULE_fa675f3a434a3d346112+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_fa675f3a434a3d346112+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56bcad5523a0e96e80ff0aad4077fb4427df4e57058d493e20a6511c91c9449
+size 799960

neuronxcc-2.21.33363.0+82129205/MODULE_fa675f3a434a3d346112+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b566d1ca9bbe809614e9c072e9e909f8c8ceb89ff61085c391bce4f157564943
+size 6872064

neuronxcc-2.21.33363.0+82129205/MODULE_fa675f3a434a3d346112+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf109196d8338da1e36f5ecd489bc4f0483167a41755481ae26722ae50d6a46
+size 7019528