Synchronizing local compiler cache.

.gitattributes

@@ -11867,3 +11867,25 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_14611821751025129524+bad9cf09/model.neff
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_1798959443618413102+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_393045707851385331+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_4395987120667329067+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_0a113de31eae6e0cd5ea+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_21fb9cbd6bc31f93ffc7+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_244d0637c526ac81b414+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_3634540e2564ed96b5da+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_3634540e2564ed96b5da+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_48e1dbda70c7b45843ee+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_48e1dbda70c7b45843ee+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_52f62927e2aef61c8a2a+ae6a382b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_7e3a1a26312c81c65e8f+ae6a382b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_a7bb15d22b2a18c55870+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_b42ea471c6d81a15b0b3+ae6a382b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_d22c269383bdc0775b95+ae6a382b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_d48baee12d51947bcd73+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_d48baee12d51947bcd73+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_e5fef74c2bea22a04c7c+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.20.9961.0+0acef03a/MODULE_e5fef74c2bea22a04c7c+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_15640073450153027801+f7f529f3/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_17272134439322064525+f7f529f3/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_17799376403849510564+f7f529f3/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_18274421132528031246+f7f529f3/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_7645671890323173873+f7f529f3/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_9669004554499106932+f7f529f3/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.20.9961.0+0acef03a/0_REGISTRY/0.3.0/llama/meta-llama/Llama-3.2-1B/59041c9140e83957fcc2.json

@@ -0,0 +1,77 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-3.2-1B",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "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",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "meta-llama/Llama-3.2-1B",
+    "checkpoint_revision": "4e20de362430cd3b72f300e6b0f18e50e7166e08",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 2048,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 2048,
+    "neuronxcc_version": "2.20.9961.0+0acef03a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 2048,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "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-2.20.9961.0+0acef03a/0_REGISTRY/0.3.0/llama/meta-llama/Llama-3.2-1B/96440af3992c61db1915.json

@@ -0,0 +1,77 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-3.2-1B",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "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",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "meta-llama/Llama-3.2-1B",
+    "checkpoint_revision": "4e20de362430cd3b72f300e6b0f18e50e7166e08",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 1,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 2048,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 2048,
+    "neuronxcc_version": "2.20.9961.0+0acef03a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 2048,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 1,
+    "vocab_parallel": false
+  },
+  "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-2.20.9961.0+0acef03a/0_REGISTRY/0.3.0/qwen2/Qwen/Qwen2.5-7B/6fc75d9e400329069010.json

@@ -0,0 +1,71 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-7B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "Qwen/Qwen2.5-7B",
+    "checkpoint_revision": "d149729398750b98c0af14eb82c78cfe92750796",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 2048,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 2048,
+    "neuronxcc_version": "2.20.9961.0+0acef03a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 2048,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

neuronxcc-2.20.9961.0+0acef03a/0_REGISTRY/0.3.0/qwen2/arcee-ai/arcee-lite/aaad74b827582e109166.json

@@ -0,0 +1,70 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "arcee-ai/arcee-lite",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "arcee-ai/arcee-lite",
+    "checkpoint_revision": "c5cb9c38be16b64757f785f0df36dca87f76d5e2",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 2048,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 2048,
+    "neuronxcc_version": "2.20.9961.0+0acef03a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 2048,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.20.9961.0+0acef03a/MODULE_0a113de31eae6e0cd5ea+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.20.9961.0+0acef03a/MODULE_0a113de31eae6e0cd5ea+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e97945c7aa39207e4c0573a12e7c0daf41de18887466041dae687748e11602
+size 679803

neuronxcc-2.20.9961.0+0acef03a/MODULE_0a113de31eae6e0cd5ea+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8755b3ca0b48f0875b7ef368ce891da56963170f4f8b46e352718100990ee252
+size 3636224

neuronxcc-2.20.9961.0+0acef03a/MODULE_21fb9cbd6bc31f93ffc7+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.20.9961.0+0acef03a/MODULE_21fb9cbd6bc31f93ffc7+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db744394a0c423f4f3bd9aeed587f1626c4bd8c310867545e7cf7ccc6a912860
+size 371739

neuronxcc-2.20.9961.0+0acef03a/MODULE_21fb9cbd6bc31f93ffc7+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd98bac47a28a2d1126fcfca9ad2579a775033448ce80b1c0350e5702f5100c
+size 9657344

neuronxcc-2.20.9961.0+0acef03a/MODULE_244d0637c526ac81b414+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.20.9961.0+0acef03a/MODULE_244d0637c526ac81b414+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a74c0049d74cb0cc9d967d1d7ea350ba916c89acfbfe54e18c0f36696e0c719
+size 660175

neuronxcc-2.20.9961.0+0acef03a/MODULE_244d0637c526ac81b414+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e891ff7e08be3d14ee7a833ea2d46a1de88887f6e44c7d103a45b6af959964f
+size 10732544

neuronxcc-2.20.9961.0+0acef03a/MODULE_3634540e2564ed96b5da+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.20.9961.0+0acef03a/MODULE_3634540e2564ed96b5da+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950d4b81fcbc51f2ee05e4b54ec72c34ed6a614a09777678ab8256ccadf4c25a
+size 740840

neuronxcc-2.20.9961.0+0acef03a/MODULE_3634540e2564ed96b5da+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe618c73e74cdd8db0825b2bc1429797edc127378610f6efc354a4275dc62f1
+size 6145024

neuronxcc-2.20.9961.0+0acef03a/MODULE_3634540e2564ed96b5da+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160f04d4186c56abdcafb441db29b46e6a05932c324492e3b7e8f82c35db298a
+size 6339591

neuronxcc-2.20.9961.0+0acef03a/MODULE_48e1dbda70c7b45843ee+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.20.9961.0+0acef03a/MODULE_48e1dbda70c7b45843ee+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d391b1d7dbf4f034f49282f26255219468054f0a8333e9e7b2990521de02e2a0
+size 388806

neuronxcc-2.20.9961.0+0acef03a/MODULE_48e1dbda70c7b45843ee+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da7c1e95569880d633b22e37a0a3595d9d7b5512a76703ee264afc7a406f047
+size 2335744

neuronxcc-2.20.9961.0+0acef03a/MODULE_48e1dbda70c7b45843ee+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106b77e6679e9a0a7723043bf22964feffa0545658a41eccf5953697cb730d34
+size 2407399

neuronxcc-2.20.9961.0+0acef03a/MODULE_52f62927e2aef61c8a2a+ae6a382b/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options='--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --verify-hlo=false' --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.20.9961.0+0acef03a/MODULE_52f62927e2aef61c8a2a+ae6a382b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03509621db932b2ad273e9eb6035e68292df17c21e9eb99d8f09d22c5cc22926
+size 69007

neuronxcc-2.20.9961.0+0acef03a/MODULE_52f62927e2aef61c8a2a+ae6a382b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f595fde6155be56d50d6da408103d6a443f33bc13593725934a650d1f79c547
+size 1352704

neuronxcc-2.20.9961.0+0acef03a/MODULE_7e3a1a26312c81c65e8f+ae6a382b/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options='--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --verify-hlo=false' --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.20.9961.0+0acef03a/MODULE_7e3a1a26312c81c65e8f+ae6a382b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a026f3c0afa9452f8e28cdfbad2e7e345e697bb30fd481c536111993679da0
+size 201977

neuronxcc-2.20.9961.0+0acef03a/MODULE_7e3a1a26312c81c65e8f+ae6a382b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81e92eb3fef01485419a56e993bff077ed797984730707b5730e493864719624
+size 6554624

neuronxcc-2.20.9961.0+0acef03a/MODULE_a7bb15d22b2a18c55870+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.20.9961.0+0acef03a/MODULE_a7bb15d22b2a18c55870+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b3c5395792211a3272bef80039b605b36847cd4a86941f65c417d19b17a1b4
+size 343143

neuronxcc-2.20.9961.0+0acef03a/MODULE_a7bb15d22b2a18c55870+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5776d9905351a073af4bfce4191a08faa6247cece91a4368db3e10ab67929cd2
+size 20204544

neuronxcc-2.20.9961.0+0acef03a/MODULE_b42ea471c6d81a15b0b3+ae6a382b/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options='--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --verify-hlo=false' --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.20.9961.0+0acef03a/MODULE_b42ea471c6d81a15b0b3+ae6a382b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3df471f965045c386c6e8db1b96baa6e68fd5adbc463b3ff4ee9e534efee4e
+size 71540

neuronxcc-2.20.9961.0+0acef03a/MODULE_b42ea471c6d81a15b0b3+ae6a382b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d54349cbc656b3fae72730ffaeadb9a4d2ed25de24bb152402b20385fd1dd0
+size 2663424

neuronxcc-2.20.9961.0+0acef03a/MODULE_d22c269383bdc0775b95+ae6a382b/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options='--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --verify-hlo=false' --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.20.9961.0+0acef03a/MODULE_d22c269383bdc0775b95+ae6a382b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27fc08e1e4d7a8468ed18e98af82fedc774d2582c19d7152128f4ce8b8e3d2b
+size 177861

neuronxcc-2.20.9961.0+0acef03a/MODULE_d22c269383bdc0775b95+ae6a382b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bd9e2f6f0168634b093fec4cfc765432ecb8c69add8da6f44065ee3f22cdf4
+size 1557504

neuronxcc-2.20.9961.0+0acef03a/MODULE_d48baee12d51947bcd73+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.20.9961.0+0acef03a/MODULE_d48baee12d51947bcd73+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e82cf9e4b37a6d040b934497f5bd95de4d2bc09d8d1fd9321190908082ef08
+size 417093