diff --git a/.gitattributes b/.gitattributes index 37c424a39a90e613f2739522e2a4821347a4dae2..3cac8e5110d9bdf62d85c69024dc1c139f479127 100644 --- a/.gitattributes +++ b/.gitattributes @@ -5271,3 +5271,28 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_7585b7b81ecc283af772+a9d440f5/wrapped_nef neuronxcc-2.21.18209.0+043b1bf7/MODULE_a89678b39464c33c1815+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_bae931052fc7117dae12+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_bae931052fc7117dae12+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/2592b69b1afedac6c249.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/2592b69b1afedac6c249.json new file mode 100644 index 0000000000000000000000000000000000000000..decb5a553da86a79ab84b32a10193291f368d878 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/2592b69b1afedac6c249.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": 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": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/f9479b3f424f0ae4542c.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/f9479b3f424f0ae4542c.json new file mode 100644 index 0000000000000000000000000000000000000000..ccfb6dee16204ccbd1acf35e1ec713029c4f18f6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/f9479b3f424f0ae4542c.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, + "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, + "enable_bucketing": 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": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/68e8a9aa766528672764.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/68e8a9aa766528672764.json new file mode 100644 index 0000000000000000000000000000000000000000..5d59fe83aa0b14d0aecb28dc736e784b5623085b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/68e8a9aa766528672764.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": 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": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.1.dev0", + "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": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/322124df0d79b4f7f8bb.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/322124df0d79b4f7f8bb.json new file mode 100644 index 0000000000000000000000000000000000000000..cc54b46eb76baf3c5f0a82eff33901afae709a7f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/322124df0d79b4f7f8bb.json @@ -0,0 +1,65 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "_task": "text-generation", + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "decoder_sparse_step": 2, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "enable_bucketing": 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": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts": 8, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..633dbed2eaa37dabdf9ee36dec02aa45f2e9d0ed --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a97bb411dcd64871e1b1784620de52aab98fa041ae87f39fee46a8518b9f118 +size 78518 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7a8003b7f1ea1d7edf638b3722bfa968cc911f36 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a2282ddf8f23c97222ece601e4f0757f78fe73c6f641b3ffd4d3fe5c24e50b7 +size 287744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4c86200906230322b4d380546c80912e2f75bf82 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01efbef13f746aece3be+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6bc663eeb8487a29b91741cdc21020abf78254b490d02397bdaaaaab3f2b119 +size 296094 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..86dbb720979c71489ac235e59ca0f77a86bc0680 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..380e691f108e93e00dd9e9bf0b9bc3a6e14db163 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61586b49e1e903cab9fff0482909f040c5e97621b59f6233899973b7cd27184d +size 84807 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4c1e306ee3a3e27778fd522f49edef71ad85925d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0dc4bd0a16b1a4ab1733+c2248236/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33b221d4039eaaa99cb40b84d626d05299fe802098783ac5418f3b32574abe8 +size 646144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff index 4cbb9f919052f116296b9f09ab5b5c3c371ad435..4b73f8be39b0687e66c93f803551ed1a14d785fe 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:be474cdb3dee1b28b0f2c4a3b2f352e571cf3a468cfdbefd0c6adb39b351d32e +oid sha256:a2d9f3177230710833e1a22c473ceb0215149d4996fb169ded5f87e0ebd9b6e7 size 246784 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo index 2b0b28b7be1a198f20d4ba3088f734e934b16eee..6947b23b1665a11411eff49c5a64caa7c8eb0fda 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ba6e863951076186e55b60309ad403bef45b8cdf8ae435cfea24baed3501ff50 +oid sha256:11296a74882475c7e044dddae990ac1e06a377d292f8bbbabccbf9f52a68de87 size 255104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..71cc5af4454da4b12e5b11d5a5cd0c9f1768fe1d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010699d8fe7fd543b752b93c8bc2cd72e5309050ab149427dfd589c97e7268c5 +size 81516 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1f401e6c73ae59741f109c92ca047d40bbced4d2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_198eb3e5a6d933feebd0+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36bf12c475e30b9ae5c3e55dc492a5b36e2b84326264d9707f19e411d4862c1a +size 267264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..cb53ce53583cfe21339b4bed39f5fa1a679cddd1 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fb9a088a70cc3ed35cd9c1c2443ce8f328cf694b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c4af19c1f6118b30a135c4553925fc304a74428ae95971dcad784cdef2729b +size 97794 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0006b75ec7688b8ab09218e772eaaef6ed0176d2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_19f0ddffb404ac2b8204+253d6470/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3706159398be1c857cb9410baa841093252d4bd2db4a6ec6e5fcfcb5866e59d +size 410624 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb index 6133acfb8f92c406c896f7320b4eae12fb3b236b..4e048268a2ebda42a903d9c30e684be97aec650d 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:02600675cb7c8ca5d1f2075830e8debc6e9695a82feca2066bb6bef97a44a512 +oid sha256:42d1111cccd29ce4edd640c6b5880fa7b920b5c1211396da06d3b58670ec7a12 size 90382 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff index 976f9cbc7201673332a20af19073c44c30c68ba4..fde2255bdb0c89a5a5638df492a98fed01c7aaef 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e14327d2f51da405e88b30418db0c11bb9debf3521db564b5856377ecf8c9971 +oid sha256:e07848927e2ef873e5477430034ef70cac7c7af77f9e216a81255e421762ed85 size 359424 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cad0fbfc3f3d7194c0b8de6b469433928d73a232 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3b6a0ea5977bf9124bbef9091daf3ab3acffd04afd968383c5df8268501518 +size 79552 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..96702f9d7b40e4e2ca9d10badfa20f552498cc41 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_243316f018b041915a7e+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e48ef0d3d4fd0d15bdd689e6cdf5d1898680cc3e8a41b478d5c210cf083bd6b +size 338944 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..7ad085fa649cf1da3b4eace6cdf4e70b954f0806 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_bdc1e7bb-6313-4016-a46d-a1410f4efde5/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a11cc062167102b0f4faa9fdf16388d72d9e0015 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4590b82eb167fd46963abdbb717cc18cb9511961a3393d100eeacdbdc45b0243 +size 11280 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6ac327671534bf4882fdac21ca81b2875bcb38c3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:592e80e1bffbd437bacb4001b4b80f6e54f1fd34a64af2d516dcdcaa57f6cdce +size 1444864 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d5c42b828df129788e611a10c4c1dcfd478e31dd --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c5098190e907f2a54fb+8c16a911/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b534f5733c6240dde4a8aab2b87c743eb5ecb9c2f13835d0623982c7bb41e5 +size 1447845 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2117dab3e3ed8caad749b8256ab430c591d3b72a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec57d9d2f9d9be197ad88a58ece6b14b0ccab97c121b8d20cc9512558ddf6562 +size 70276 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..389986f6420c8d5b0f98999feb0b5b86942d2cc5 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c575672250d5f23841d008ced6c33f1df62b6d57923b8be0b7797455ae58cf2 +size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..617ded72a276d7638fe3fa89d291e1dc6af446a3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05228c5d86d72717d585b6556529ede68ef62b4a306d5d7bfaf5f07ef7d9d96 +size 289571 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8aa1efec651d6c6dfe05237c7181891c361c80af --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_38e9154d-8e64-419a-965f-d7efa146aa17/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a11cc062167102b0f4faa9fdf16388d72d9e0015 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4590b82eb167fd46963abdbb717cc18cb9511961a3393d100eeacdbdc45b0243 +size 11280 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..049797fb9a080a28cb4ded7aa83b76ab6942f7f1 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:245d5e7af27461459b0791912e0f89c33a9493848539058559a74a829b073d7c +size 1444864 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..12aa5f66ae08bbb821701429ca89274a264cabc2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6aac25f548c1812d8b53+088d889e/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba8a5b414833177ae5ffb36be31595fb5032512541b3ebd43555eadc356280c2 +size 1447845 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..d1f1bbcf75feb5ea0f64e3347bb1d71771e3336d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_9c56f973-ecb5-4e85-aeac-6fad60b308e6/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8496781848c02ecd308b5b2c5a3c342b702425e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e79a5cc325f9a317d158d931d75ec73ae1cfb16a4d83343a2593edd95d0044 +size 8979 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..153a42da959cbb02ed93e703ccfea31303f5b640 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12120ae8f7a60e70b9b15515259b5090bb5827c34359dc4b47b59ba4856098aa +size 246784 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2941e039db1b0c747ffdabc71efbc32be023e544 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_72ee895d32151757c529+d36b334e/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01aeb7504192d925aa66afd6766e1d163fd38409c0e1fcd88b72f63c92731062 +size 249608 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..449b5720c5911938c8c44b129fe894a3eb514a18 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_bf39c7e6-4d0c-436a-8429-901687e99683/compiler_workdir/NeuronRMSNorm/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a2752c25c9f7e1092e2b55c010694e168610ce3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c774c6626fc91684e924b843c1fe807dadbbac6d8a8e19443663b43c13eac35 +size 1165 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d157ad6c554dea593844b5c49ecd17a87ad75db3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f508862404b94b0c5f1c77e0e44f08299b9fb64c7224bfcb31c40d79b71b9d +size 103424 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3b4e287ba6f30f93512d0d1e818937df690331b8 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9bc951663ff96735f71e+aad90931/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e5a3ad1f132015036421817714ed868e99cf4b92c1430b8e5151e705cf4e9c +size 104320 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff index 47935c313a1b4c349bf45274cb3e63448a3f783a..82abb82374c55b8fe514a43f6c684dcf66aa796e 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:40ffa4c2b1a8bd699eabd5c72a80b84ed771f0105eced55f7b9b13da8aeb8391 +oid sha256:c6dba7c62aa41379f9b1362ec08c4a98c7c5a74f1e99be09a8ea6d1a512a7372 size 543744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo index 40609703bc63609010f83a1fc97a28e0cbe8af51..d83acc0dd5b1f73207e5c25238f699191c322b90 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:093f2c67a771901b8ca6efd4cc10914b71b3bc2274c5047aa923491c5fca89d0 +oid sha256:8516abb72de6f5c8d2b9ad74508eb524c404b4dbf23acc26daac265ba6925161 size 563380 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3b28dfdd4b213537b2dea5c6bcc967e9c9762156 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/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-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..757acf24be3a9d8ec5df52a73e520031a1b7069d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aac12629bb09a3f29593e822adc9258c99737b4f857e6fc1d78284fea075b5d +size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d932a4dc0113ea2e873d1acae381acf9064e3b61 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b26694c7ca7ec7ec6e04+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db0772da52a0bb2b152a5ed85c72eb32f7e865604c07c0d0d40db2980016c27c +size 285854 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff index 9f47fe33e0e13cbf24646f0fd1481469d0dab8b0..56156ccaa5698a6741ceb3f082a2a99df68b33b5 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3df3cf6d998ee655a4ab528b086e3fd141717662a93fa0050345ebc65767d331 +oid sha256:0b61279642ab3f4895869ac9220451ba0253a65848a0ea4cc5f727f78970ff3f size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo index c3c59bffa15763aedeb6ef0079a3f0464ccc736e..1766967e3a09d034e0adc5cb4feda25531ea6de0 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3269c2c8f12aa76fc71cb4442d2a32596b20e46841a799b466b3f1504ad2db13 +oid sha256:717b264eed41092c6a186e7596770239039aa71701a44a551fae1b51b3a3fc3a size 289031 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0acda2091419ffefac552b387c604242c216e220 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0209401219006cca96e01930250e97052c586f1267ed95762a3fd065de8cbe9 +size 83504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c749246a95d9b4924f615b0fc826a2ffcb3045be --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6450080bc47619254df+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3be943131798156033b5df1ddf7aeaa12171fb23e4115c6048429dd50c9ce02 +size 328704 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..64028cc78541c1833466a343e251d2e19d025203 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70386c0d4c7acaf312dfe4908f119fe46d817ab3d82394d549c5ed84707d551 +size 80382 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..63bf496eb607784c0e8506e2b735ee208526d3f0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce5e959b8b423ae1f3d90425e5bf6e8b650943e80f178dcae24c9822386cc2a +size 216064 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f22e21d74c5cd9512e07747f147570fc77878600 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e7bf36a5a3a95f1e548a+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a95fe8dafa968bb5e4852ffddd4f721b765275db7a6a3d53c2ffadb6c27e04 +size 224412 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..be0ba40f70c99b047e474501f9331c01e99cbc52 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_79c7e93e-2793-444d-8250-493cda4dd626/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8496781848c02ecd308b5b2c5a3c342b702425e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e79a5cc325f9a317d158d931d75ec73ae1cfb16a4d83343a2593edd95d0044 +size 8979 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d726c4c0af4ec5507e85a27f05c6d56f6d9ac32a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92410f3650ee33754e762b2fc5f854f1ade676aec848b3fe74e9eb021f1d9c64 +size 246784 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b2e86c9e3846254608e45c389f2f2786d015ab7a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10462aeebc3ef8701906788c0d868bbdaad214aa964e5c575c5eed6c8c7c4f3d +size 249608 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..93354bd42abb66b9b6e56b127441174baa403534 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..727fe2caac58854e2f659732c11b6b5473ac4505 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6596d3769509c9146ae4a3975d1c70c2eb236f1527bf8cab5cf9306c4300289f +size 89555 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ae865be9b374885c2fc48ad4210998bfa5b31822 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f541888df5d30c3d67a56163a1068c3692ee9ada874e678ab7254fb51af0cfeb +size 369664 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..97aa5f33bb794c16f3aa9b236b2190d234e0990d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f4ada83ccf930dab43a6+cd3419b6/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c7e5a9a1208751581b37d797ce8d5b5e52f19f045eb31cd2ca6f5149d7c038 +size 379362 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb index 4c9440a6dcd8c6f56f168f6593441a566f6984d6..a291eef6371ee0cd154490c84b4b4979190709b3 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cec6b5d749ba16b2de638bf1df7431fe2e43da05aa54851f276d7647ba88c5d5 +oid sha256:df5b9b5d719971d47dec5dcb4d4b5bf90ec5f188bf96403d9ef0053c49d97724 size 82772 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff index 29b42b61d3414fc46168ab2f991dc01e5b5d065e..c67c004fd985288462c0ef18268b717def94acea 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e4eef61e2c1dff014888bee516c930535f9079d5594e478edc9c4eade7026c12 +oid sha256:b9572352e721af4c0c3a2c56e76a4b5ab2ae9605d4829aea3fe819b4329163be size 267264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb index 22c24fe7d072e5df0008ec7b82df6c1ebe73f660..d7ac504dad1ca324a321baa4d7ed0d98d9e0079b 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d8cea1685d29853d3461b266fc7630a02c24397d66e3896bed5b3cdedb728876 +oid sha256:fed0bc9e6a1063940352f77cf3c69fd69dfe037f37ff904cce52c6b300a4a81a size 694128 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff index 76222172ab22eb690c622c9c91fee8417cb00b04..bccd5738420a9038361bde5e17daf9b65b46e23a 100644 --- a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ac903b6b4a5cc5d3c9f923db50534efd2212faf0a366a3578200f63e564d83f1 +oid sha256:a99aac18d392a7fa78c603ee2eaa429959a523455a432a6bbb186be4711f1396 size 625664