Synchronizing local compiler cache.

.gitattributes

@@ -6731,3 +6731,8 @@ neuronxcc-2.21.33363.0+82129205/MODULE_fc8e09ebb5e540fef7a3+24129607/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_fd0e003c65277ac495d4+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_fdd8f98956e8286e2bbd+fb4cc044/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_f69d5fca815f1db46810+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_6b4e994533e8b4f49a4e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_6b4e994533e8b4f49a4e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ad0a77ae55980efcab6b+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_de6e17941451fc284800+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_de6e17941451fc284800+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/0c951f51f53bfcc30b6e.json

@@ -0,0 +1,63 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/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": 2,
+    "capacity_factor": null,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 2,
+    "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": "0.4.6.dev0",
+    "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": 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,
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/a7ff21f93e0cb0390d57.json

@@ -0,0 +1,64 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/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": 2,
+    "capacity_factor": null,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 2,
+    "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": "0.4.6.dev1",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 512,
+    "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": 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,
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.21.33363.0+82129205/MODULE_6007347d914257cec196+24129607/model.hlo_module.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e19259e1f11b34e91536e9de4c84d84994a4c886e057e84d41c0987bb94584
+oid sha256:22b20c5cd4edf89b48829ae2e0e4ba8863c45c633664e744543ec1867f74f9c5
 size 435061

neuronxcc-2.21.33363.0+82129205/MODULE_6007347d914257cec196+24129607/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2deac4f867d19e11a1bf5aff36c5bd8f16282a013712f52453f115167b5f20
+oid sha256:e76d386e4211d647845f98e0b30e1a8444dbef3971a63444cf441e50fe42663f
 size 85750784

neuronxcc-2.21.33363.0+82129205/MODULE_69a9c88448dc7c95dd02+bdd17ecf/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_df2a2860-5f2a-4cdd-87e5-57065464ac25/compiler_workdir/ChunkedPrefillAttentionModule/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_69a9c88448dc7c95dd02+bdd17ecf/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59bcff2dbd1961e3494d0436c1ada6278a9868de9428fdaae993726230b1c176
+size 18111

neuronxcc-2.21.33363.0+82129205/MODULE_6b4e994533e8b4f49a4e+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_6b4e994533e8b4f49a4e+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5314e9b2f568a450bd1e54d8eb951988eeb3dac44d48444b79d2aa5ae88429
+size 426769

neuronxcc-2.21.33363.0+82129205/MODULE_6b4e994533e8b4f49a4e+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0fd8eb39eeb515b9cad8e188e5b5c1fb3067fe85413fe0e2654226ce622a17
+size 2499584

neuronxcc-2.21.33363.0+82129205/MODULE_6b4e994533e8b4f49a4e+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad012924f9bdebc1cdc382027c94ddbda572a69bdb96696d5017338d177fdf2
+size 2573671

neuronxcc-2.21.33363.0+82129205/MODULE_782036f3eac1b6db6d1b+a02c3a36/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4328ccc260649ebc72e8e4de1b77da8ebb2d91da591bd2532e2c3dbbacf687
+oid sha256:f67609dcb979de7f4344f80d47f408c449f3fc0daa4761f7e0e98d441965bff7
 size 1741824

neuronxcc-2.21.33363.0+82129205/MODULE_782036f3eac1b6db6d1b+a02c3a36/wrapped_neff.hlo

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b27361020bc8d5ed27320a7c17463fc994418088ee83d25efd9842b36f75c4b
+oid sha256:a65cf109c5429e55ca0f30dc373c9fbb4be8126bec97f00e17120d0d694045b0
 size 1815793

neuronxcc-2.21.33363.0+82129205/MODULE_84fd59187fd6be117f3a+fb4cc044/model.hlo_module.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128abaed1aadd52fd9f95f287daf5aaf3dfe175895448c0aaaa437b83a0d30de
+oid sha256:9a0be6d1ceb8c9002241395262d7825ea7c83da19ad6ff21ef6cb3f18d3c0d2b
 size 573205

neuronxcc-2.21.33363.0+82129205/MODULE_88e3f2a464a5aa09c071+b685a559/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_05643d66-49d3-490f-bf5f-59451294f9da/compiler_workdir/MaskedSoftmaxModule/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_88e3f2a464a5aa09c071+b685a559/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c694be3799f7af69e675b5ff12cb5cc0a37c5b497506b666f215400c90a69457
+size 11756

neuronxcc-2.21.33363.0+82129205/MODULE_8aedc67936f903a2b9c4+fa9fbb43/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_bff3a7c2-efb5-4f60-b8c2-db045c20d793/compiler_workdir/MaskedSoftmaxModule/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_8aedc67936f903a2b9c4+fa9fbb43/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d0dc25b69fb5f42eb56f3dcd1dde0eaecaa712b2d7d4ad8d1b10b2868d85b5
+size 11756

neuronxcc-2.21.33363.0+82129205/MODULE_ad0a77ae55980efcab6b+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_ad0a77ae55980efcab6b+24129607/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05ad527dd98530ff1934cc0978bb11d88331152209644114965f2b45a6643fe
+size 509366

neuronxcc-2.21.33363.0+82129205/MODULE_ad0a77ae55980efcab6b+24129607/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e0fc56822f8939bf4339e34cfc3138ec4a04a0fea224b58242ee952097ec84
+size 41616384

neuronxcc-2.21.33363.0+82129205/MODULE_cae8a0ee9677f6f7b542+6170d8e1/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68343986474726278f99537638223997b40aff3ce0002aa57d6454b1692f960b
+oid sha256:248855ab5dc5241d90d7946bdcb39ee97ebd8761a30c53e4adc24d310451fcb8
 size 2049024

neuronxcc-2.21.33363.0+82129205/MODULE_cbb1dfc823681d5ae498+309a8c57/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_6024004c-37d0-4f76-83c1-a93500b20a5c/compiler_workdir/ChunkedPrefillAttentionModule/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_cbb1dfc823681d5ae498+309a8c57/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b34b4e8f78bc3f4140c746f4366b9ef6612f31b6f16f3b5c6d41a25b454feb
+size 18111

neuronxcc-2.21.33363.0+82129205/MODULE_ce7e2a2399f408878a1f+24129607/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e293b66e0df86f7fa9301d0cd2ed15c6f30e25a8d2bdd5193f1f62de244ca9
+oid sha256:0f1b1d60e24ca26b6d24cb49e566580a8186b53bd77a98f8846cfac45aba635a
 size 2612224

neuronxcc-2.21.33363.0+82129205/MODULE_de6e17941451fc284800+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_de6e17941451fc284800+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8082affd359097cc7f0ada8fc2e6c1aa607d78966eb6044f76183537f3dcc94
+size 442128

neuronxcc-2.21.33363.0+82129205/MODULE_de6e17941451fc284800+a02c3a36/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc847a88af8aaf34e60dd3fb31c8e399200cb63872e28a209ca44bf63a9845c3
+size 3134464

neuronxcc-2.21.33363.0+82129205/MODULE_de6e17941451fc284800+a02c3a36/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15bc6289c5003685d709a9fce7714bb031d576f67bc4a00ecfce890f95da10c
+size 3208565

neuronxcc-2.21.33363.0+82129205/MODULE_f9b5b25ceb35d0bb7f65+a02c3a36/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47c739038d7d0c4558a9741ce55370950d838523f79ebf89b548ac9703421bf7
+oid sha256:3b2412e661b900b3af3139b1d91bdb93c5ed605c4b1865838d1e1547d8bddb2d
 size 2366464

neuronxcc-2.21.33363.0+82129205/MODULE_f9b5b25ceb35d0bb7f65+a02c3a36/wrapped_neff.hlo

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3c500859dd6337c0bf4801346d00c542e7e2349e996c6f9616b5021b1c7c87
+oid sha256:5f876bcfcef6adcc92879cc76bc6a8e37ca4579da8523aebda542c9a7fb43556
 size 2440436

neuronxcc-2.21.33363.0+82129205/MODULE_f9cbba0a80402ac769af+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_f9cbba0a80402ac769af+a02c3a36/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfd3d1cab714096c9000baca69c2dd20fe8f9ae854d60c8c267db5f25618825
+size 392731

neuronxcc-2.21.33363.0+82129205/MODULE_f9cbba0a80402ac769af+a02c3a36/model.log

@@ -0,0 +1,3 @@
+Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/token_generation/_tp0_bk0/model.MODULE_f9cbba0a80402ac769af+a02c3a36.hlo_module.pb', '--output', '/tmp/nxd_model/token_generation/_tp0_bk0/model.MODULE_f9cbba0a80402ac769af+a02c3a36.neff', '--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', '--verbose=35']: /home/ubuntu/optimum-neuron/.venv/bin/neuronx-cc:4: DeprecationWarning: numpy.core.numeric is deprecated and has been renamed to numpy._core.numeric. The numpy._core namespace contains private NumPy internals and its use is discouraged, as NumPy internals can change without warning in any release. In practice, most real-world usage of numpy.core is to access functionality in the public NumPy API. If that is the case, use the public NumPy API. If not, you are using NumPy internals. If you would still like to access an internal attribute, use numpy._core.numeric.normalize_axis_tuple.
+  from neuronxcc.driver.CommandDriver import main
+2026-02-27T10:30:31Z Pelican exception: Unknown integer type size at /local/p4clients/pkgbuild-const/workspace/src/KaenaCompiler/neuronxcc/pelican/bindings/python/PyDType.h:__LINE__: