diff --git a/.gitattributes b/.gitattributes index 6905a62a26e5d4d1247af5a85079ae1e8256c091..d463afb2beb4aa6acdd9345656207636561ca5ea 100644 --- a/.gitattributes +++ b/.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 diff --git a/neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/c86ffcbbf6e956184167.json b/neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/c86ffcbbf6e956184167.json new file mode 100644 index 0000000000000000000000000000000000000000..7be3f700a20431a0489130c30e11362d63a6f837 --- /dev/null +++ b/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 +} \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/ecd2f7d047b79655fe67.json b/neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/ecd2f7d047b79655fe67.json new file mode 100644 index 0000000000000000000000000000000000000000..1625856c54ff384294ce99673e31a476c56a5268 --- /dev/null +++ b/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 +} \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..249ac56b3d6cb7d1c7478ef6f3f2b3bb11520ac7 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a116fa4df515088c49889ead6fb7bbc6c2c5bd4d --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_02637dd85e9efa05f8c5+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e3084282eaaa7f8031716a2413579b223851902c --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9792e9f02bb032371f2848e86e7400117d1ea217 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..68dd3d11bf3d9b4c3be580323a4dc4f78ebfff1a --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_1a20278f09f4dc24c5ce+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c1eb40f80f3f3f21c9dcf754befc0dc35648123c --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9ce249dbb530e7393e40e6527befdcd24c2c58b8 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_205aac4ddf40e8cd8192+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..423669d3bece29f48a3b8e3efae9802a325b678a --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..48d9ef622ef7875721ac66010d030c39fa5ed8ea --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_24b25c4ef7dadb159d44+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c441163057a2dbce7a917d2b4d96cbadee42bc15 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..974608ddfcb70e4241b68257581aad5a261346f6 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_264e490ccc3eeaff67c8+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9d414ab720dc110f216e5d52ca3d8b5a920de3b7 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c5425bd2a1c826df23384bfd44c0cea8026b2517 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8c4693501af2bba5ce6fb37ed8e745a1e93484c2 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_2d8956c2efa061692893+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d9926bb2a659a6043b9634b756c548e430625a2f --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..62558acabacc9b7c5a13dcdb2fe8751ea39d40df --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_2f03d0e5b16407d9982c+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..10f983805f1e10fd7b920eea562fd35ed3b44ef6 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ac536f97b963557292c0682decc9db1207d6d723 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e1875adc8b71e4b05087e21492324c727e2c2121 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_4766b3ce9dda37ad5647+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3967b327ae73943bb9746996312762412f4a4061 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..857f953abedbea2407911372acf0532fe89f51b4 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_5066616ba332143954ce+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e00d546c34dc542b87322223ded4ec882ae0ec76 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b7792e10c233198e3a67ba2bc38d7ebce242cde5 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..62982c52b385de8ef94fc905fb9bdbf171ad3224 --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_6198c514ed33053d2227+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e8e2f01014ee8be4fa552272b89cb3063655dd9d --- /dev/null +++ b/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 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7e861b40edf2b1f3dbb9d15328e509cf413c9178 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32cf8d2d4a9b422ec6f9e81461ed4b484e30cb2d9163179d3c1fd39befbaece +size 219357 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6bc77927e11aec500a9b2c68b28464ced1b067fc --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_64804268780c2ee66221+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee9e1ee1c9cdc7d05fda52f281efd50d2485ebf0af912318fb7f3d71182b983 +size 359424 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ec069fe0c5de0f42f47e17fc0f70dcf967678d0b --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea0b1a5212a13a54164b33d614589b516af9b682f4f050df5c76dc99ae6d723 +size 200922 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..93b04a66b7456f08840107769f762b702b03f601 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_78cf2f3e0df6aab3509a+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad490bcb992eac133097f2d13c970be4603a9979de19370431e83c1f094cbcf +size 369664 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f7c5f026b255b2a12e1efa61d86e44938b9fa27c --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0464f6ca3b45912cac809c7234b62807104f292ebe4db827377c8733578fabdb +size 2114384 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0c00a075efa41ceead542fc1fb75e9c2282b24d0 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f516372a678e98e6025bd12a3f6a7782de14981ba599e44f8d7613b46c4c7b +size 1874944 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..91433a4266e39c906c2e33387eb75fa80b7f78b1 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_7df9ee969f5493357c7e+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a09cd6012a04d9a4fcabff0abe029a8429404df7020eeb383c0c8292a861594 +size 2031135 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cc50555b6b5ba5b3714d6a87f1947399adf9425b --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3f74ee6f964333df18238b6024ad4a71afff8315095d626a471197163327a64 +size 237516 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..341c4e95ed4458a2a481325dae3a0b297a25dcf7 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efa24dd66eee1c2c0a8821ffca0d827d7d4bfab1e3c561b0b391f3fb2d7b39d7 +size 359424 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1fcae99d0f7c951adc030ed35f847b5c7839c33f --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_8589b616e6e3b8dc2071+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c08661bbe4c7c0e7c24b69f19dcf1ed58ab699233f7b764ebe6be491daeadd6a +size 367637 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3de4cbc6d6c61c2a00227eb4a558b3d09fea1c25 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4632b89a4a12207d992dd276444fd3b9544d2b5e69f99569e89a228ff2efd6a +size 226761 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8eb5fc7cf2c7bf7a1578ff5c8fdba1d222b1cb69 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_8f969cf46966979b7453+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e2884d8856bcd664f8d1d39a2860225f6c89f82c75a26264e08ea79422bfe7 +size 830464 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..7a30dcfec8c337fd5caf60e88dd720c9eeeee345 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..213d7280de9a996c510e0f1b9fae1136956e126a --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad757da3c2b4cb51709ba0a3aeeecfc0c960d726f406a716da202efcbc8ca942 +size 1249852 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c747141e7156d9b34dfc270af483f502af44d7e3 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_91fad9a5b1fe20948b9b+781055f7/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f26d8fea8b71accf6e825a5333476ed437e91fd57279aac7a070d04a1c67f232 +size 4056064 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..78f10c9834cb09a877d3809d115f2f2fa9adf85b --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/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", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..03abf3e1750b25ed9d8607fb06d5c6d56a67c150 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e750b24ed26b8f3f12159b758e42886fb92993a70ae0b2e29f2a83b5f9d200c8 +size 1400307 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0a1c44b30482c0f1d92cb18b504aa7261a7fad09 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec34845f957d2887bdb8f42c2fc48c6005ad47ac77c45199341395bc527daaf0 +size 2591744 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4799aa770652f46c766dd9927603b6a3daa5ad12 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_93e63f51891501ebb0dc+dae43e99/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02ea21f145f7e6c710abb0ee609b6d1d7c016bd773ca9e80ef811e2ebb966b56 +size 2665943 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..797d7e09f396f439e54b3ec5dff5ce23082c4a87 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:869ee2eaf4d668e0caa87f01fa48e65954fc224b241ebed3400576ba16bc6b8a +size 239186 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6e30b53887300f0f7ebfe6ae6ea4320fa2bc19d2 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28222dc134ec7483317cfee027da8f8c6bef2f183cad5bc560157cea620f9049 +size 318464 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..af1931349eb9edd32028c112a529ad823fcd1c27 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_951033f0828e95301264+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc786f00807f8e4c11180e2873608f3748fa58286d878f14dcc38eb121a6bf2 +size 326677 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3cab62d41dd5a333755c51a010c5812a49d2c582 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e35e067a2f07196db5e7e536b25aba29d6efcac9839a81d95d9b42aed332a4 +size 226761 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9dea0994976b6c041d5278699e08f481ccf539df --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_96ec8ca2a9c7ef4226cc+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3bb23fd71b7dd1b62a9090f0f687d090880804bc9b8922611025dda48277b74 +size 830464 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..56a72db39159559ce469c2fc520567366b02bbff --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--verbose=35", "--logfile=/tmp/tmp371c2yzj//_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b642fc63111802873d192e2a133947880258e8e0 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da4861cda78b67caad3bac80c6eeb50f0843724b473f217efab804f26ed2d73 +size 3581 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7befe76688dafcfa17c32b8bddbaa892213f9af3 Binary files /dev/null and b/neuronxcc-2.23.6484.0+3b612583/MODULE_9b4b9fea7d397b02f9fd+c869d6b0/model.neff differ diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..60b007e1812eea3d6f43ad6dc35329f1f01107c4 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc9ef017892a3fc417119472da0b3483837004de334c65b4169037937665468 +size 225603 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8c50596c63a6c8e6c2eb62c04759852d47c91535 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_bfe2ac8bf837a0025a6c+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:901f02458b20dd553eb4d8c7952668a7445ce37e5d5d29e7d97abe6002ce8b90 +size 830464 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0df79ea78f5c140ab2574a195e21672b6400e19a --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:588264b64160d4f20c30fc780e92a7b276c1e3496ba80223703fa8f63df311dc +size 236565 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..06ab0fe615d895aae29b12506a5f259366924fd8 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9aa30d0e526e80be4358c867109b203281c5272f922fb73f98392ab94de5364 +size 359424 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..41d941b68552305777c4a528e5d707aedaa2f0ab --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_d63645a6681632b03d0c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a73acf425997bab0a7362241b1eb63fbb3479d776a341d11344159b218c7893 +size 367637 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c9c11af354f88eabd54235e52dfc95cbf41660e8 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281e0c8130e1975e1ddeb465c96f1a26b1c442d50ace7095555b153bbc6f0a79 +size 236565 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..37c7f4e47b60b49aa5d0b306bfd9830645792f19 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a6cb7246049e37a6349be280cd3a63baba96a36d7e4bde86ba29ec408e8a4b4 +size 359424 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1ec0e0bb2f4007ccb076ad0a37eaf0546b2d5f58 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_d7d2a23a0d647ccd894b+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32883556f6738c35280f3b1825311959a174db2d68cf081ed4cf6b0f5022ffd5 +size 367637 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1fab4fc7bde211006eab91887ce9d97f8a688979 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ded451408cddbe5bb9d2eb9998b267f5bff985e33940fe1e0100e1719d3faa +size 226761 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a12e4fbcf3fbcb9dc759ad832c66e364029125bd --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_e6a8ab93a90acdec11af+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a1530aad263d41f5e8c5d422a8b6efb96cb2b89e3bcbcb4e9853351f4ce91c +size 830464 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/compile_flags.json b/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+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"] \ No newline at end of file diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/model.done b/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/model.hlo_module.pb b/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fef0e9217b6ec64d255fb36aad0dfe70efd7f7f9 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac1de86cb5694b38ac9cb5d5e81f7f591fbfdfa8f15bf70d40bf3198f81b359 +size 236565 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/model.neff b/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..176257f1407e5179f49d48fec2916d038d175c33 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36d45d3d5924dc4e45340a87d27c3a03ea3077f705702d72b79e183238d2c707 +size 359424 diff --git a/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/wrapped_neff.hlo b/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0cb8dad035401db7e55f98b65ed0d2f7dc9511d3 --- /dev/null +++ b/neuronxcc-2.23.6484.0+3b612583/MODULE_e9d79973df9286231fef+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2832e2afc46ebbffd72c83a7b138c25a7e37c26da3d31681868d4edc26ccc716 +size 367637