Synchronizing local compiler cache.

.gitattributes

@@ -5687,3 +5687,22 @@ neuronxcc-2.21.33363.0+82129205/MODULE_e54f2eec2036cfaa2527+a02c3a36/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_e54f2eec2036cfaa2527+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_ebda959e0a7e1b1b3d41+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_ed0ddf13430a2a717168+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_0654da519a1110a6aad4+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_06e58c7a469128c652b5+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_3cb9043f67e6b5a9acbf+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_4262eabf33a3b2c61448+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_4262eabf33a3b2c61448+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_57d02543ed097317eb38+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_6df16d281c8d34e7b8c8+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_7776165b0d0d23f46d32+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_8d519e024abae9bbf305+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_8d519e024abae9bbf305+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_da7e97c0c4b45f3b3821+ad9e832d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_de35c230ea0abd3360a7+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_de35c230ea0abd3360a7+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_fede9e304a150a635925+617f6939/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_fede9e304a150a635925+617f6939/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_818bc30ba0942fe4c3d6+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_adf2c812522e586cea39+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ccc2d4abbb67d5b7286f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_ccc2d4abbb67d5b7286f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/MODULE_0654da519a1110a6aad4+ad9e832d/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 ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10  --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_0654da519a1110a6aad4+ad9e832d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c096a64f827fc570914bd877c33bb2b6d4b1afd2313a82e249d70da338f146
+size 936785

neuronxcc-2.21.18209.0+043b1bf7/MODULE_0654da519a1110a6aad4+ad9e832d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c15732a812350a3a27aeace7738a30c6027911be1dc5e6a5d896ff890d7c00e
+size 11561984

neuronxcc-2.21.18209.0+043b1bf7/MODULE_06e58c7a469128c652b5+ad9e832d/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 ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10  --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_06e58c7a469128c652b5+ad9e832d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c5f09f68c1912103423eeb9d56a58404f0c6fdddbe1816e7c33073e659a2cb
+size 726384

neuronxcc-2.21.18209.0+043b1bf7/MODULE_06e58c7a469128c652b5+ad9e832d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68ad0966b1e9e7ea97f6212f6275741342159f8b013adca888b4ed2564a7a4c
+size 492544

neuronxcc-2.21.18209.0+043b1bf7/MODULE_3cb9043f67e6b5a9acbf+ad9e832d/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 ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10  --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_3cb9043f67e6b5a9acbf+ad9e832d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb5bd8e78159ccce3eae8b4e36beb1bc30d66f673c8c4d01b80e818f0e5483cf
+size 678558

neuronxcc-2.21.18209.0+043b1bf7/MODULE_3cb9043f67e6b5a9acbf+ad9e832d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a4c486f03a6855de565b9571babfa47a4f214c4242a94445cc972c72dfedf5
+size 1659904

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4262eabf33a3b2c61448+617f6939/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4262eabf33a3b2c61448+617f6939/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76aa5bdd9171b91554e3461102196b55b4a8f7453a965cdc9e9c89b9746deda7
+size 747576

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4262eabf33a3b2c61448+617f6939/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405817d784b623c7bc20cb7ce54f7d65ed8a737226de9755f081bf73b10c95e0
+size 3113984

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4262eabf33a3b2c61448+617f6939/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95fb219447af7158351ee48861dbcfbffd673c4fb243778edef7c658333a80f0
+size 3299472

neuronxcc-2.21.18209.0+043b1bf7/MODULE_57d02543ed097317eb38+ad9e832d/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 ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10  --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_57d02543ed097317eb38+ad9e832d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7889bc62e8dcef2a8de07ab0712acd532c2d6f207defd057f42dc19a58a0dc7
+size 983272

neuronxcc-2.21.18209.0+043b1bf7/MODULE_57d02543ed097317eb38+ad9e832d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee37fa3f3fd8eb8db0f8f866970dfdccc1d45a71c42a03a5da62f6ff16ea6a2
+size 11981824

neuronxcc-2.21.18209.0+043b1bf7/MODULE_6df16d281c8d34e7b8c8+ad9e832d/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 ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10  --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_6df16d281c8d34e7b8c8+ad9e832d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97fb1218b3b85f5e1750c92b0b95e18b2f0fff0dbe607f1c8307ff625175c782
+size 598800

neuronxcc-2.21.18209.0+043b1bf7/MODULE_6df16d281c8d34e7b8c8+ad9e832d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789d0cd4da08ab7421274e55250c231edd04c5dab1294fedc165ce26e13ef622
+size 297984

neuronxcc-2.21.18209.0+043b1bf7/MODULE_7776165b0d0d23f46d32+ad9e832d/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 ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10  --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_7776165b0d0d23f46d32+ad9e832d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7683c211dc0af38826ebf6230b77d074a161cee9ec7cb1479cbed80886141d
+size 879322

neuronxcc-2.21.18209.0+043b1bf7/MODULE_7776165b0d0d23f46d32+ad9e832d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359e60c0c6954b4b1e41353841731e1af857fcdfae77175beede8434fa5b0b4f
+size 11664384

neuronxcc-2.21.18209.0+043b1bf7/MODULE_8d519e024abae9bbf305+617f6939/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_8d519e024abae9bbf305+617f6939/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5071a7599bf37c6e189b6187158a0179ccca7462c9dffd2a1c7bd8018789229d
+size 764473

neuronxcc-2.21.18209.0+043b1bf7/MODULE_8d519e024abae9bbf305+617f6939/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314b069eebb2613c82e93cdce1a0e1e98cc3f8b83d87c475b1be547e9b715902
+size 8397824

neuronxcc-2.21.18209.0+043b1bf7/MODULE_8d519e024abae9bbf305+617f6939/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc685dbef59db678dce409552323ab8686c2f8181be35c3a56d908b079d65c6b
+size 8583322

neuronxcc-2.21.18209.0+043b1bf7/MODULE_da7e97c0c4b45f3b3821+ad9e832d/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 ", "--lnc=1", "-O1", "--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10  --verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_da7e97c0c4b45f3b3821+ad9e832d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a1aedb62ddf41c80dc68cc5012e85a308184096cc91161a0b8c3722ed7e519
+size 667112

neuronxcc-2.21.18209.0+043b1bf7/MODULE_da7e97c0c4b45f3b3821+ad9e832d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8b0200b2ad3b8eab8b71726ba5c3f59f83e8e5fb23c82e56699848db128fce
+size 451584

neuronxcc-2.21.18209.0+043b1bf7/MODULE_de35c230ea0abd3360a7+617f6939/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_de35c230ea0abd3360a7+617f6939/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:005f593253160ac83985c31e41ad06d4e8ef8abb217eabd8f83f8616b96d0fcc
+size 623022

neuronxcc-2.21.18209.0+043b1bf7/MODULE_de35c230ea0abd3360a7+617f6939/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c9ddd19d822c930094daf4f23fe71ba2ef0752147d8d2f02c968f84b64b932a
+size 1537024

neuronxcc-2.21.18209.0+043b1bf7/MODULE_de35c230ea0abd3360a7+617f6939/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777da8f3b00fbf3c274133ae4405c17c52d5d2942b92d8423bc02639d1b597f5
+size 1720482

neuronxcc-2.21.18209.0+043b1bf7/MODULE_fede9e304a150a635925+617f6939/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_fede9e304a150a635925+617f6939/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7707b4ae5ae2b0aafdac9c76d4726c1969cbe176743da0ce7d7ad494ae57b7f
+size 743609

neuronxcc-2.21.18209.0+043b1bf7/MODULE_fede9e304a150a635925+617f6939/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1816edc19a32a1152161f05f69ee58a6289d6a4bef3c10b547245abd13e8333
+size 2970624

neuronxcc-2.21.18209.0+043b1bf7/MODULE_fede9e304a150a635925+617f6939/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41cca0b61d997d19bcb4eb7bf9d5d2b64b1e0ed7c572644b2097d98b1b2c918b
+size 3155208

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/3f2788536ce52a84f6c0.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": 8,
+    "max_batch_size": 1,
+    "max_context_length": 16384,
+    "max_topk": 256,
+    "n_active_tokens": 16384,
+    "neuronxcc_version": "2.21.33363.0+82129205",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.3.dev2",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 16384,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 8
+  },
+  "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
+}