diff --git a/.gitattributes b/.gitattributes index 6e963e9203ca772054161b8c4f9bf8a5ed116dcd..5cf8bdcab6792f0708bbffaee30370ba190fbe71 100644 --- a/.gitattributes +++ b/.gitattributes @@ -6168,3 +6168,27 @@ neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.neff neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_728ea12fa65b10279163+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3/llama/llamafactory/tiny-random-Llama-3/e16b019c51f845891789.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3/llama/llamafactory/tiny-random-Llama-3/e16b019c51f845891789.json new file mode 100644 index 0000000000000000000000000000000000000000..db045ae4b533c8fe0e3b6fb40c0825e45b49a12c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3/llama/llamafactory/tiny-random-Llama-3/e16b019c51f845891789.json @@ -0,0 +1,62 @@ +{ + "_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": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "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": "0.4.3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "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-2.21.33363.0+82129205/0_REGISTRY/0.4.3/llama4_text/tiny-random/llama-4/06fe21b7c35243f4bba9.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3/llama4_text/tiny-random/llama-4/06fe21b7c35243f4bba9.json new file mode 100644 index 0000000000000000000000000000000000000000..5428c10a3641f526ebf924a938a9118f6c38d09b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3/llama4_text/tiny-random/llama-4/06fe21b7c35243f4bba9.json @@ -0,0 +1,81 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "tiny-random/llama-4", + "_task": "text-generation", + "attention_bias": false, + "attention_chunk_size": 128, + "attention_dropout": 0.0, + "attn_scale": 0.1, + "attn_temperature_tuning": 4, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "floor_scale": 8192, + "for_llm_compressor": false, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "interleave_moe_layer_step": 2, + "intermediate_size": 64, + "intermediate_size_mlp": 128, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 1048576, + "model_type": "llama4_text", + "moe_layers": [ + 1, + 3 + ], + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tiny-random/llama-4", + "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "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": "0.4.3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layers": [ + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 1, + "num_experts_per_tok": 1, + "num_hidden_layers": 4, + "num_key_value_heads": 1, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "tie_word_embeddings": true, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 202048 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev0/llama/meta-llama/Llama-3.2-1B-Instruct/534b7169afd0669cb851.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev0/llama/meta-llama/Llama-3.2-1B-Instruct/534b7169afd0669cb851.json new file mode 100644 index 0000000000000000000000000000000000000000..2827b5b56ea2956dd0f53c1f4ff42a02235be48b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev0/llama/meta-llama/Llama-3.2-1B-Instruct/534b7169afd0669cb851.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "meta-llama/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "meta-llama/Llama-3.2-1B-Instruct", + "checkpoint_revision": "9213176726f574b556790deb65791e0c5aa438b6", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 1, + "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": "0.4.4.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 1 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+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_03def246761e956f7a81+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..24b80e03bd02eb9810e873210c6a4be17542c188 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b0911c04d1a1f3cba5e5e77dcb1605b3a39eb823f45a2645cd969fc52f2a63 +size 389975 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..97283c69bbbe0bb0cd2630bc77bada4c393f08d4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77cfb7776c65ad90fa220e5207223152f0e725bfc73a917149dddb5eec8b79e +size 5633024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..69caad50074163b0ba35f71ccdf3b72ffe447da6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_03def246761e956f7a81+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fa880602fb3a301629e465c6a877077f25928b70ca435815df251f07425bc01 +size 5707929 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+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_306829ff9e3811933fe7+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3b28dfdd4b213537b2dea5c6bcc967e9c9762156 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d61ac2165fde7772e8d3035b0f89b50beec5e0d305548cbacc624eefa9452d3 +size 82753 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a7bf5e9904168d8e8399cd22594bcd2407a1aa25 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e63b61edcd20b2b6c18802faa1c4c4067acb53a0f0603d4faabc7f2d7add610 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c6e54f98b6581486eaaff952854e37f68bad319f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_306829ff9e3811933fe7+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59403d318f2bcb77b55553d070b94acabd3bbdbc52da0f20e804759a51cdd6a5 +size 285854 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+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_574e9a764503b48fbba9+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d1fe139f27af1feda34e7f5299f35cf47b33834e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3810428d8bc2193c766cd607d41079f3021e3860107b7580c4158183051b8100 +size 1061093 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ffd864775b81dc2f22830416852e7b6bb435b8b0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_574e9a764503b48fbba9+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b581f570131f39602819f273cd00c47873372b06194dc7cb33c9c5dd15bb32fa +size 9473024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+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_5f6f4f62aba29e11d946+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..448a81f18f49904d2b0c536b2266bf9755ecf0b0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff29a9d610dd9881a52dec279a06be490a45580450ffe418a317e9eb5295330 +size 694128 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4fcd92c87d1fa503b627e9420f5a0b41c257900d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5f6f4f62aba29e11d946+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a5bf9bbaba0b0f3abcb6c9408d5be74ee9fddec0f3a1a933943271af767839d +size 625664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+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_8414d37eab328896acb7+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e984f1bfcc67f74c845bbd03e125247152b9b6bc --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828b718ac0d544f14a9a683c76b442c49520573027ba2e8347fdd5e79531704b +size 702870 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..10f37b65b9642bca789c1b9b93f8d42c3176357a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73bb9f42bc0c9fc82cdd455b1df42a8d677843e6df2cdaa0156d783b7a884b4 +size 3503104 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ff2e1df6bc106f8786a4fc4d8dcfe9df7f478aeb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8414d37eab328896acb7+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027c95630275e4b5fedbcb1e196c594c6ee27e9450d57d8c29e3da0f97b4bbe2 +size 3640300 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+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_9d35248a93d4142a3cf1+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7e04210cffc6a0d4394c1c53e9ce2842bb7a3487 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff789deef8176afeab268439fb0770b9b965fd178c19b0aead0f8be9a02e0b6 +size 739558 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d4796c84ffec11a3cea6126ae5f966046983590b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9d35248a93d4142a3cf1+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f516045352a9ee7a801257fbcdc2acf8ec33bfc172b6bfd19e961216ee11254d +size 26133504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+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_9e174a0ad6384712cfa5+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..49f4c5600ee3466d8daf8d4d48320b162eb6c512 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2091cd37242da699619a7ee893e9cd7c02bb92c4cd99e0ba1ffec00be7827fcb +size 83504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f94ce4a7a64f24d80100e42e53145db7f0c8c525 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9e174a0ad6384712cfa5+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f67671a80c4bec27cdd099109748d4d5d7ff35f171ba81528abe3c6eb5bdd473 +size 328704 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+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_a38bf2241a80d200aa33+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dc80e75232e7b415325d1562f9518f26670d13ec --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f25ade0a3f52e4ef283ba2768a1420e559bb8c5c6ab4b261c432d72a52fc9e6d +size 863510 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0d878728389f50804d97fb19129cb16c74bb8ec9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a54421adaac8624539899fec33dc8c608ae949455c3bd1a97d068c17abc28eaa +size 6769664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0916f324dcfe682c70c73065e5b3de82e527676f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a38bf2241a80d200aa33+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a398b3a74d052420d442286f85440cb1c2491ded5182d08474c39b537c0ed3 +size 6936331 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+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_c0808787f3555a6627cc+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dc48797913dfd76b9dd538afe0d4193c2b11c64a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0ca28f6aa86847fba45aec92c730116dca2fd2549b970fd744ceafbe276fd5 +size 865460 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7d8e84facd60e45f39fa54c39a4941e9487070a1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c0808787f3555a6627cc+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fee68fdda56ade80ef20eead9552203f09b3c7b075091ffe419527eda0b756d4 +size 36148224 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+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_c2b3afa51c57d431a332+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9c5a330b9f7fdba6bb4c837889e33f6c9e6384d0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c2920e5fde77a80d2d66c9ba5addf46e53d032f533c7097cba34e31243f84ed +size 588406 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6613479327e5a5d8536a9230ef17f16b7c910821 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8017f2ca25aa30c01e839314f958eedb8512833a8e66bfd9d075b9943b0980c +size 1926144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..500a4c375a6256896e24ee775c66a65011a25d1b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c2b3afa51c57d431a332+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be407fd3aecea94529ce6cc1917f9b19dd88a49aa9a67cd85524e1b93a5b54cd +size 2082478 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+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_cedace9d3d693aab8d35+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f9aac85f572373187ed5932ede47f59a7a91323f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0902b9467e36affd529236be99c466bb326eb59e56e6b6414b2bde17d7913ac8 +size 676474 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f1e30ede4b1cf7aaa3da444d570e6923e7bbc949 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec0baec640d91e361c3b362f2fac70a2822318fd5354c94664fc2120715beac2 +size 543744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..95077cc93d057feabc93cf82504cd5f56b015685 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cedace9d3d693aab8d35+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55203eb44348b2c8bb0ef5ea518e1398574ee528543b486e731873e6a7ce1001 +size 563380 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+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_d5ada2fae774253484ca+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..07decb260a3582b1e79d7cb6a69b9eabae367e9d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b91b1d220f451f3a76b0d2ced5025d99e4de456f85f913167f26b27a27166cc9 +size 509380 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5445bf25c122a7bdff0853e71d56265bc3085b1c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d5ada2fae774253484ca+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acaf9f1e0d6a20192270db1d6dc2f6bfb7772d8d651fad66d9d494c2a1737fa6 +size 41585664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+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_e973fc6fe6bd9c3d7c03+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d873faf2dfaa8b158baf749fc04d5bdfd1465b40 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6820471cc3742b4adf59a1b20142e67c937c1514499868f53f2b80d1077c6f62 +size 418223 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e26834e07f0f9def36d630f028b77131b9d79bba --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:255147310dca63b96b5b43d33e19c9049e4b4be35dba9850393fd59f04ffc0cc +size 3093504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..bf33ce7f552d0307434d0f13d9b9bbf9882cfd44 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e973fc6fe6bd9c3d7c03+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5a5169a4d0836878311fdc8809ed5c5817b02d7f71aa8771afaa75fa74d803 +size 3167748 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+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_f81f36ad8e744c8da4f2+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9ccf48cf90bbc6f70feadeed769fcb2d08ac7391 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:474d64755e014d1e74b81e1ed0db386baba3ce138beb5aef0fae1cafdb9306d3 +size 480020 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..114cfca235a5a3c3c1a464940406dc37e1bebbb6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f81f36ad8e744c8da4f2+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2dff6720dd90001b455fcf20d14163f659f22105d6abe748822147c0e38b3d9 +size 84624384 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+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-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ecb236a32d48263c71af77009a3864796de88270 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03c0af3f77e20436709250cd93beda007a2ff4196b68776f515d112386a41ea5 +size 2390316 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6e3304b717633045d512f7b757b1c218952a2da8 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d9e21c05b09ac3a01cdf74d5dbdf461eb02d4bab34eeaf33673f13ed8ce5b8 +size 13671424 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4ac5496cccbc4380bf01affbc91763b2dc12aa45 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ab3e50332a1f49feba2d+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c7ca12c4359f7fef2cc3853df0363b4bd7fc9dd32f359255cbb91ea030fc32 +size 13818440 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+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-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..992cd9f9d287e9d1053a417fbe6dfee5f2becea7 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce5417df13ee8df347aed8f282ddbcb2e5adbd89cebf03e1a4407327966e1df +size 2363942 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1e3eb28df562e77b68b47320d8fe8006a3a69088 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ba94bd052390e13a7dc4+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a1f54724851ff51444a8bb46f1b82161994472728caa9cbbcaa0a8f70038b4 +size 5366784