Synchronizing local compiler cache.

.gitattributes

@@ -7481,3 +7481,39 @@ neuronxcc-2.21.33363.0+82129205/MODULE_cecb0adc6b331de70195+593aa068/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_2331738b55a05fa07ce8+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_eda1231b39877cb3b060+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_eda1231b39877cb3b060+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/c86ffcbbf6e956184167.json

@@ -0,0 +1,83 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 2,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 2,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.23.6484.0+3b612583",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.6.dev3",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 0,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "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_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/ecd2f7d047b79655fe67.json

@@ -0,0 +1,63 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "llamafactory/tiny-random-Llama-3",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float16",
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 2,
+    "capacity_factor": null,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 2,
+    "max_context_length": 512,
+    "max_topk": 256,
+    "n_active_tokens": 512,
+    "neuronxcc_version": "2.23.6484.0+3b612583",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.6.dev3",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 0,
+    "sequence_length": 512,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "float16",
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "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-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79037e0f9d2e77c6e7c92dcdcd7ceef3797b3c7d023ca751d32046e1696a36c
+size 237516

neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ec2237798551e2019bcb7a2a37b3c4b634069b3e2d3b4a76bfb9c3d38e73bb
+size 359424

neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56da60b525584c073151c94b91208d3fcc69427953f7b2efa3f8cd661cf2270
+size 367637

neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1993a4e2bfa6c7aa41efae3d7ba5f15064c3c8c6bba593f83f3dc6177a5a06b7
+size 217544

neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5b08a5ea845c9a5b2bb768bca2078ffb0c3826eef1ec7a2a22538b27cb4ce7
+size 318464

neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d880a6c76c33a563adc0c68ae98b71620b78573f06c61043cc85fa9f68e8356
+size 326677

neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d09a1913f58b00a5c5e02ae33f97e1bfdc28e5459b74cfd74bb2e458fc2ce80
+size 225603

neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce9def3c512faa97caf89f89a1ac6e5b7937ef0cbbbee1795214678f963b176
+size 830464

neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ebc86d7c9f547bb67860eff415fc90ec441a074c80b416e515c7d893fdb628
+size 225603

neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6347097bcc5455faa4aeb0519dfa738627c3673763fc0d1ee3a9497aecfbe7f0
+size 830464

neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e92b86a440607a0e965c1f283246aacea46ce4b8ff9950f5713e446d3abd2f
+size 226761

neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b4ab2709947d2d1e3b4d4bf17c64d988f0a9959e6e3c2e97b814d348e8168ad
+size 830464

neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42e1758644396d9909552dac89e4a39c8ba23fa0dea0779625b5ce426350c89
+size 237516

neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853925ba9e2d58a8cb5d2e2c73ca9a83ad7363da3b83255641992d0fb2a3ffdc
+size 359424

neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:075de1f97ae7f5a52b8adc2d6cda7231ba9293d0d0b368f4a0340282dced04ef
+size 367637

neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc73756f288dfce5de24577f74870f5d254400733f150081ba56889ac115e189
+size 1992405

neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12029c6ca0a61c6a169990d3f20d7cf2a8338858e6adb8bd6d89ca73715cd8b7
+size 4035584

neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b1d9644aedb95a431d24afd2914fe85276e77da20913c52ac55e06ca005a7b
+size 237516

neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9bb2b8d1f6870d1bd647133d87637ad62bc8e80dd1a5d5f4cb2f21edba9af5
+size 359424

neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4342947a9e1b35bdb523f21a7e30d3d1d928a0769994783577fbb0189564d1c5
+size 367637

neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813c89459235e66997e273a0b92c3e07a789778d1e363c814411787005c51f1b
+size 225603

neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975ca9edf817ff6f7e1bdeb078c49193a1d7b58e1442e8baab9b9ab1a5ddc2b4
+size 830464

neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb3bf4ffd5f9850e4b3e189c42d653eb96e6692bf6e03830b613f4edf8f3457
+size 236565

neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df259509bbcb4ebcfe743dc139858713dddb2d0e6c1d5a4e44861551ec512c14
+size 359424

neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc9f470e707ef8a1f3995ccb28da3b6cdb1061af9fea4839f5e6ad619b2bd2b
+size 367637

neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]