diff --git a/.gitattributes b/.gitattributes index 15c27e85b701cf06a7bd837fb2dff066e5a05890..d34a2134e49de1e9fb2773a74c9a3c3516334546 100644 --- a/.gitattributes +++ b/.gitattributes @@ -16552,3 +16552,34 @@ neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/model.neff neuronxcc-2.21.33363.0+82129205/MODULE_eea79ad4b5b63ff68d1f+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_fffa4c481b28ac601395+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_fffa4c481b28ac601395+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/4409b94110a511ee8fae.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/4409b94110a511ee8fae.json new file mode 100644 index 0000000000000000000000000000000000000000..1e51108b7a110c37cd3b3a4a13b38211d846ef29 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/4409b94110a511ee8fae.json @@ -0,0 +1,80 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "google/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "google/gemma-3-270m-it", + "checkpoint_revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.5.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/9fe76ed73880dddfee60.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/9fe76ed73880dddfee60.json new file mode 100644 index 0000000000000000000000000000000000000000..1975827945847583b1f85e33c4b99fdd5c2d9b88 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/9fe76ed73880dddfee60.json @@ -0,0 +1,80 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "google/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "google/gemma-3-270m-it", + "checkpoint_revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.5.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/ca8ebd0dd1c56ed002d7.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/ca8ebd0dd1c56ed002d7.json new file mode 100644 index 0000000000000000000000000000000000000000..6caf9f89c5d570f0c825c8edefffa11c27f122c4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/bd8b5aaeb4693c199f97f6eebd1bbca77255bea6e0ed042c0c592ee5adccec97/ca8ebd0dd1c56ed002d7.json @@ -0,0 +1,80 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "google/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "google/gemma-3-270m-it", + "checkpoint_revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.5.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/gemma3_text/google/gemma-3-270m-it/4409b94110a511ee8fae.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/gemma3_text/google/gemma-3-270m-it/4409b94110a511ee8fae.json new file mode 100644 index 0000000000000000000000000000000000000000..1e51108b7a110c37cd3b3a4a13b38211d846ef29 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/gemma3_text/google/gemma-3-270m-it/4409b94110a511ee8fae.json @@ -0,0 +1,80 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "google/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "google/gemma-3-270m-it", + "checkpoint_revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.5.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8e3ab54c06f610630cfa439ca3316fe4365ce563 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_5f9966e0-514d-4e13-9b7a-a5fb0c27cca1/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9d336ad1190cf7534c7bdc2415db43ecaacb186a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eab14f002e51d52ed01d96ec7833c4ff77cf28108c4b0f1ba5a4256cec871f44 +size 20055 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6ccace40ed526039da83e4f1f15d47d2c6525b00 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6647ec86502f59d4bc9f91c30f9636297a00c9be517842831ead2450e7cf442d +size 144384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..8a5185736acaf1e3a48be59e9c4b92071cf61ded --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1258357038924531d65a+9781984d/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60e907335ca7cbeeb116e37b6d9efc9af29613ab3b5936de32e5e62393ffd7b1 +size 152103 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_17476209562158013765+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_17476209562158013765+e30acd3a/model.neff index 09c3decba036d4911fec054f61ef2c3a11b0927d..16454301701bcde1e8cc715e4bf84698b69012ea 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_17476209562158013765+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_17476209562158013765+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f65e4244c596a897ce361472d596dbf4151e41ab --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde78f832bf7b42825123a2072be02643a57f95cbd882555ecd842f6d6419934 +size 708855 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dd346957000e1da4feae7efd038267077fa616db --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1af22ef97be0fe871938+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af5db1b519fd304a769ec6c3571b8730b8f69c2c047ab2289f4d15a66c87fac +size 7660544 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0a0ab5a03014abb4fb9472ade863de0b93862d7b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a0120595235859cb5d3b5081228df5cee5f5b7509e5089c2e0b6a2ffdf54cb +size 692215 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..301e2ff94b25b01eb6e92af4cde12fbf1478c04d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4df5bdd88883f7b8592e7ad15fc56ac4677efbdae065aa8106d8df7484bbc69 +size 1045504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..de8a89476d9ae30bb806564fbf4a34f846d631fd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1b5fd23da565a2f62ae1+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3948819097df7a66219c39985f00a04157938ea56636a068d74f644e3d7b6e06 +size 1167896 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c415d4f268bbd0ac9ab9077765f9a4dcdab611b6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9f88a7adc91f3c99012a220709f8d0099fa64358b63acd3f16030322f1b134 +size 669533 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..09ede7d026f6136f053b23f884196a76b7d79418 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2c2347b5dccbe5eb00d1+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b6d32fe855702ba97203b0c9eb3a5446060950a269f4450c8b6eb507786e37 +size 1813504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c8ec7db850905f0e9c444ab2fd4bc4e3d0a1b2be --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:318ff99081c83cf153684d419f67e6f92b73c74b6486c0937dd877e49e4ba542 +size 699082 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7e0085169ced1a3683f3d41425e3019ca8f55d45 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57ec40f5bbf770e15df1c247db392d419051dd35f6c932e3a93a53660b266a2 +size 1793024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..64fcc0d40065555b210868c3a55c9b61124aa76a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_38fd7ae3ba23ea0fba3d+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3ede6c5cd85357ee4cf8009b98d60f7f17ec70de0f5c9849dee7d32abd7787b +size 1915416 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ed53b68bfbf9f899d8744c5c8a3efba508720b2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_c8fa8278-d095-4975-a132-7e34528bc463/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..71007682787d0f8d1b4068fbc4350513bb35b9ed --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e145d2c1f69646ad6185ccf2ab6e40e023d18c98298a31281afd17759228cf3a +size 15907 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..07faef0bfbd60167cd1ceecaf94cffda6ed5561b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:876560c847b0b4e90d582baa69d7ad73538ffeb9ca7b8d9fb428b43246c64106 +size 707584 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1e2948493157ed767037d00ac567a766b71139ea --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4eed8422a5466be619c5+18574365/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f876494d415ba816ca2bb7f9de1c8229c9ba01c1a84dc3088e695d256480a142 +size 711550 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..886ac294f37fc778dd94770ebc93845a3b0f6e67 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_7534cf8c-b224-45c6-86c0-f01d9c3944eb/compiler_workdir/NeuronGemma3MLP/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..530f69ab2de1a8a033648eed223969d8082c2224 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17a7309352127aaa945d8632b425c2deb5a5e784ed4854193113d3bd8643540 +size 1958 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..93e95e9aef11a719a883d864ddb4c768e59012d7 Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7534a1be51d7cb5fb3ee20fd2d62863aa2ebd899 Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_56bb5c48d0db2bd77a6a+fcc30753/wrapped_neff.hlo differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..6d5ba329a8edf602d0b9cc7c45d23c7dba72670e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_596a05a6-131d-4f52-97c2-1218c98883ab/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c67d0bdee686136bee3b0e6351ea1367474af3ae --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f2ec47100914dfc3fc8af9739d73eed6a06058f4c6df424749e311f572d2694 +size 18364 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..173602dba63246de52e96e1f488fbf2d1cd7c8bd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9bcce5c2a75346e991e7f0d20ffdcf7f640bca02839aafd0a79515ed0a7fc3a +size 144384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a2ec3f57332dc1fac12b9269832a347baf771bf3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5aa9832a26f2ebbf219f+b075c184/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d68d9a7fd5893c67ddc82df8fca7fe60cdb5a743cc375c85f3dbf35c028b331f +size 152103 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..26d3b9f21112f5a94b8d4fc336dbbc8b58af0120 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29cad13786fa765386b03c15c001f2f1904fa92081c3f6ac9686359bef4d80e +size 567509 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0311fb22be74e1a29d897009d65bcec13dd885bb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_614f928fe1aae4555d06+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5d03aba2c6bd35518ce07e85fbdb17e8492d8fe1f20d39548af8d20603a850 +size 7158784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..7afc192778c331d18a6647a1ad9d4aff83c234b6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_ae6488d1-6ee8-4dc6-89dc-051226392a26/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bdcaddaa381975aa9c1027c88aff6df73590322b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6496fa8b5ab1848353914f6396a4f1b2d7edee3ef4c0bb00cc0616bbb2073ea +size 20055 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b48f9c4924108be0e2b91e2f51f8452390580ee0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356f7d905ec8cb1fa2f24be5ce9c3279a04bc98a3a831ab809e522fa03612336 +size 144384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4d7668f1c8863c947a1af68bd0031ab4775666b3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_68ebea36baf59fdbe1cd+e586ca94/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111224a2d90e801267aed3db5609db73b9ca5105d3de5e1278c423e982dcf884 +size 152103 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..b7120f416b7465c97443c76980bdc498ea05c72b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_deaf07f8-e449-4256-9f8f-9ec06031db49/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c67d0bdee686136bee3b0e6351ea1367474af3ae --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f2ec47100914dfc3fc8af9739d73eed6a06058f4c6df424749e311f572d2694 +size 18364 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2968613773a83dd8e2b04486edf29e8b20284ba4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd0b245df1a329196b8b4fc9beaa0b3ea46533a7c76b6a1721727544f30ddc9 +size 144384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b164c705dea1e68ee53702caaf183dcdb142c850 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6baf4058963a96bb6ff8+47ed6e95/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61152bae2345fd021b729c1f17f617c0f3a75a38fb3e558a10dee1aa6f68fc93 +size 152103 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3c68a10f27f50ff01bce56595952e2f28a370b84 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_5ef368e9-87d5-42b6-92b3-ab6340ca1d65/compiler_workdir/NeuronGemma3RMSNorm/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ea6f12c183837be29a5c8dd7e9cc818986277e8c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d035c8c2187b6398d0a4bfc66bd707e42a0d6ed470dd30071eb2dcee32a91c9d +size 2549 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a07ff79231d33571b93638ba637cb2ff71fcafe6 Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a5fb9e3f9c3d723869cc44165b9a0a1bc5354880 Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_6bee37df30ef55366c3f+463386b7/wrapped_neff.hlo differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..eceadc2bd1aee1cf234a106d42c971eee0b85230 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9784d05730e15de6d1cf1791873840a6995583c3a7a29e3ac5701802fd609f3 +size 528187 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fce424379684c3582ff2da19a3c528e2e1796931 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_79730fd9b44fc62d1b2a+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd0aa634225715ea311d2426849ec89cacfb2b66322132c6ea28fd4c31f147fd +size 18791424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e39597d73fc732a2aac7487024b29a4dc1310f46 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_c687bd42-3baf-433d-9da8-031229c95a31/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..72876fb9b64ad7ea84f89ceb38741a9618a7f3af --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:978eba486a7af969957a80909bbbc17358bc6580d9f9a60d96fe30b96fa01100 +size 27311 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b8350aa3c441f72d2f439bc225669afd783e948a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9400737438a1ff72dce17526f9ee16da3cea104d644b2ad0bea42f9f3bdce1 +size 154624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5d553f3d6aeae7343d4a605cc2e02a600a9c9b6d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_975648b1780210c41a55+7f755e5c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7193f33fd924c0ecdb861c0a8bb0830d9df62a492a20963b47e1a5014a6f7838 +size 162350 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3757148042b6db2f1f30c61868090a40b428170a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa0120d1836d43ad7fb3f1b80ed70dd291c4186068bdc2f78883fe1b049c9317 +size 558526 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f4be788629c80f6ca1e11fa34c115acbeb1be454 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa7e89e53da59339fefc41ae45b2ab75ae5873910ba808597500f7edddb13324 +size 1782784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6d202565f3e48700a615059d034cc43047bb4479 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9e3d9cf368e5890200cc+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1808d006505f45c8ac0a1f69b562f3959e5b7c40677da3e9aa5897e612e82c39 +size 1905173 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..de939fc678d83c5874bc71b68fb0d1b8286884d0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc9980209b96c5b9cd842953a264275b22adf233db39cfa566822522b055584 +size 566028 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dcdc09a43071bc6521084dc5fc9755bafb1964e5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825f66ab479df997684b11bc5daa0483fe77f5339218f7ce56b1c565675173a2 +size 1403904 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..567ae46e11fe0b6e64799585e6a23b3f9b772cbf --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad429c06448e5e133269+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab174cb8fed788f1db993fc19c839f1f13fbdf5fff9b75fdee57da5ab44a560 +size 1526293 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c716694924c07bd86b1d28587f831d09be4a01c2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a230d0583e76999ae9c598433ae6e58748f6e0576c5f59fd2e40c479535cd16f +size 708855 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4fb680c449daddc11776994b908e2a36a561e41a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d6db01106f253fc7b776+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b4d44a7ef6a00174f04fd0e3582f3b2ab2506e54f1c6534efa9811357aaeb0a +size 7660544 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..183482f0b6d2bde54f8179e2b60d6e7c15056ae2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_7d386cea-50a5-47b1-9bfc-2f72be13a4e0/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..47898fe556ffdb1a7bf974092e825b2bf803f626 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1491c97a9c506ad3023fc45985bfd2f5e1865fcc7f28e9319cc11709c7998e3 +size 18364 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d7a097007f60d0a9f80693e89dbf0b66f6c12898 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4536f639a377820b2161d97e86854485357d320f6814e6525b4912cffde3306b +size 144384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c3687844b4e4877148ad8a3b197906b261ffe621 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ee19db2c56fd49d922a9+1177c897/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c89b771842740a704aca1811b12a266291448ac2e7d08935f63e9b768871429f +size 152103 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2e6093a8e2c0a55896ae29b8ec26dcc5efa3a213 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9da4b130a1408ff7fb0272996084fdfdb12183853e3b8a2849686d0c07e0d6 +size 699082 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cdd2bd1d433dee65ed2ab6b508ff4a4cf2bf48e6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6690b004795423fee4f05e9adb62198826a53ed08f1ba9698e5ea433d7f238f1 +size 1793024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..571445690e04f3d80b85f4256f59f50c0ce310f9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fb7c14df8ae0afce903f+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:865eca2130ef2992aca8b893a2c92910fad9692cc33fd23fbabef42277aca001 +size 1915416 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a3a3b8bcebca85c738a6da39f58c4e1c8e101de0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_559ff09d-33dc-4033-829a-1cf659ee9011/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bba9d8b682596df05116940fd9b10d35f48c2286 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be3ff5269bbf302864755575d072d0a2d4e242f922bd9d2f5894a71218214fa7 +size 27311 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..77477d88d42fb3fb39a8d4433353e7e51f6da8e2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ff7f89e80c8e6f57eed8e10b10ac065ff8ce32c8b6884bc7420e4c4363ed00 +size 154624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a92d2d5662703ceef4f80b187d405ef5ea812c1f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ffb27087e7fee87434c8+10b1ec0b/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea11ac3b62ba950470567e3a6e3b790e7b52a683f5745558fa3ebf18bc35b06a +size 162350