diff --git a/.gitattributes b/.gitattributes index 3cac8e5110d9bdf62d85c69024dc1c139f479127..1e37ce104a537890c63d85f7351a852131a08f9e 100644 --- a/.gitattributes +++ b/.gitattributes @@ -5296,3 +5296,24 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee146796c3abc2c48a55+9e46248e/model.neff 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 +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.neff 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/180ffc12360632ca0552.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/180ffc12360632ca0552.json new file mode 100644 index 0000000000000000000000000000000000000000..03037bf66866b329d1f65e4883e992de02aeec35 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/180ffc12360632ca0552.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": "trn2", + "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-3/4df385f6aeaa42fb9756.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/4df385f6aeaa42fb9756.json new file mode 100644 index 0000000000000000000000000000000000000000..0625873f707a25e734e9dbfdb7f1e15e655024d9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/4df385f6aeaa42fb9756.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": "trn2", + "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/b787c4dd68458fa32228.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/b787c4dd68458fa32228.json new file mode 100644 index 0000000000000000000000000000000000000000..9ad9965e8cee3b4cd3cb3dc5b3dbf0673f2ac304 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/b787c4dd68458fa32228.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": "trn2", + "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/2502f9dc059367ba4857.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/2502f9dc059367ba4857.json new file mode 100644 index 0000000000000000000000000000000000000000..3b11f3f95e91d25738912116981ed4ee6127c502 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/2502f9dc059367ba4857.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": "trn2", + "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_1b54f21d033a73ffbcdc+a3f02148/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..6314cd417258813cb7d558f37a985f13422d4a69 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_97f69534-a6f2-4995-adc2-d7d40068808d/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_1b54f21d033a73ffbcdc+a3f02148/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a2752c25c9f7e1092e2b55c010694e168610ce3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/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_1b54f21d033a73ffbcdc+a3f02148/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a9eddf961eb1b25dff10ce7f35a0612bc0d6cb31 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5b096badb6086196ec5a04499d8965d0c198bf3be7cde2e994a3ae44d106c1 +size 123904 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..85adb182c5c25d484290c012625d5727835d3ef3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c8403de522d314bb6bf3090240712eaa54c727536d7d054514ff3ea393706f +size 124800 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--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_24cfc117f33f64ccf2cb+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d949ae2f4aa3f8178844696c513d8aa1a4494c7d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a6eef6ba0f2f8f2e5b2b08d0b1267a1cb9f5d863c6a9663b8734eaf119d5c7 +size 1299219 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..79fa0ccc250a403137055ac9da7fc92ee4508648 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d4107a5d0bd4ba3554f897e6813755bc970d8a204e1d6b43c18a6d45b9017a +size 656384 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a172a33926889ce6f4340045867d8094a11e207b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_6b4d1de6-ba8a-46e1-b742-8132c4bd3bf0/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_2ac190bdc4561a89b8aa+5ba4a294/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8496781848c02ecd308b5b2c5a3c342b702425e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/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_48cf67a7f3630493577f+d0d57c8a/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..59897bd765036ef87720c3a1d1544b79efa0dc19 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--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_48cf67a7f3630493577f+d0d57c8a/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..60353e3e7034f0b0cdf08b4fa9680250cc421785 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c051e4879cfd8bdbf2d56c9246144686cdf549884c14709e9a26b9a0cc7f646 +size 1338548 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..af083cfcc9ae987ca4b2e48dc5af049a2e47e455 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1976a4dde9fde2a2b9ed5c9e9560c7003622dd4a301111dd8cf47e3dad9c9882 +size 646144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..29a9d944d0d49c41e662dc382de9b0729c8775ec --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5471821b8db21496fcfb39dc4a8b0b5aa7fcfe98b7480c8497f8ff717f97bedf +size 655842 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--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_4a2b64355e0bb619a721+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f44fac22acb575b06778919d848d9842ee4dab7d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61fff4fd459f6f5b9436447069544757836fd8c198c2d87f985898effb2e01f +size 1124430 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5110ccce111c827f2266396caa2d54e7882fc48f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e330b18cc3560dd7ac1256b72ea18762742985a49cf46e59aa6ae1b75a1ad73b +size 451584 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..90c01de768b0367611f9e5f8ef3e4aeca45cbb1a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--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+0b01cb42/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2117dab3e3ed8caad749b8256ab430c591d3b72a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/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+0b01cb42/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..466eb2a828a0608522109e684b635b573a218a58 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddafe107c9ccd625e44c60097b05c006d5591a36d01e1d8e997e8b69be0fb2e1 +size 431104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c55b9437903d977a983325b460001836ff7ffdc4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a1335ac17ebfa49e49622676cbc6563c7b29018ab34cd018858af4a3aac85f +size 443199 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a556a0c3f8e6705ba4eeae0523a3af763396f569 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--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_6d90bc000559d461c79f+564b7b5b/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a73032aa62b64f59904c864d3e40e18fb14afe33 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b999ea9ba89a487255da2b130a2bdbb271cf57445eb26ac94e78bd297c00b1c +size 1365236 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6c42fce619fd78f2dc8bcd76417cf7d36fec4426 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe57e6c82ac454d00dff3baccae6b36d5841c3b369aa030a6414bb8d4e02a9d +size 687104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--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_7387ca39d94080c41e25+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a0aa4dc52ab243ea73ff56bfd246ec338fb4b71c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77782fdab9f56144e7d5c218eb8e23aa06187b6bfbc1434af59c8ae366258595 +size 1302867 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5889efeec95f6f117f1e5ee67a2e5982fe934b2b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9faefa6276b0561549b3f3ab9f7cb04fe7d6b312259195c30c152c84578139 +size 646144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--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_7af2912e9b351fcd249a+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..90a0b36272beca28ea907b55fb62d14744874c3b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4d5ebca4732581ccc5392f3c3130051c9b01dc4710efd3ec99ce56f613df40 +size 1280147 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..238a9dd012f5b2be0ab28d7b1db130c32e4d1269 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfbe9cc8894d956087bc7c3317a0df313f6e8e4b49e74b38669803c9d2120b03 +size 594944 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7986443fdcfd240582fe074ba0a3bc9b64f766bf --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2d8671898a565e03f8068814a8d8637b8ca58e9839847b9f7268e52f5c7a6ca +size 602863 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..facdc7ebde9f335b53f32ab5035719092c602bb9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_c1269219-9671-4c14-9da1-4397b35e378f/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_7c1663040965c8138539+313ee46c/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8496781848c02ecd308b5b2c5a3c342b702425e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/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_7c1663040965c8138539+313ee46c/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b07fff09ef6cac6461c39181cc76418133817af7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce4188259ebeabb332ffe619985d7daaf343f25e4649408ac88e022cd2e0a3ae +size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f50d96e7f7d63fb5a82203ad4b3e976b339ee7cb --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5187b88130966d0ada116d44c427f93585ca2c0ac12359a54ad0efe396e843 +size 280328 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..00bc32d086d98a21804c160bbb6a724b8d3ae9b4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_fc8e4646-569f-4184-bf6b-d8e0eb33849c/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_a87943be1c24879a03e7+aa7059d7/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a11cc062167102b0f4faa9fdf16388d72d9e0015 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/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_a87943be1c24879a03e7+aa7059d7/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d9cc39146274cda18187d8fba545d989a263aacf --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431e4e5ff922d6a474980bd9387beef3e5706cee848cb766ec7579d640b9b872 +size 1342464 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1e1f5dc341ea777102a6aad4dc1bbb0c3f076e9c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2488bfac557f30118c56f44c7f30a606b473ac1f03ed7afbdec2aab8fd4d846a +size 1345445 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--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_ceeb2de518f3f121f9df+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ec02fd199834ea0a773adb77719273938b72936c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e2ee6b950bfa3400e3b5a8c05d6257832092b337036fd44961b079ce5a9887 +size 1284382 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..156dab2990c56d3bdf721968075188796f659047 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be57fc082672bc63645da219807a53a9d988bd4cac2176ee3bae166008ad9269 +size 584704 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..990a490b7498aa39f587407cdf71e434b41714d2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79c97f9e4a4ce5b4143c8d8e4f2c8d86cc30cc0de3698feafc7d01afb5534483 +size 592623 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--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_f20adcf25e6f9d0f0500+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4c18bf4179e6d0313fbf2eb32d0ed1ad310bca60 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337addba1531c5577d5f4e7ddba5378c9fed5362e83a4eef93553a3d75d9d0f2 +size 1123231 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..767bb7e5cced77df0e9a57da1f647c1eaaf034e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23c8a2383c3a8af60cf85132748bb0d667926755ad35b00b8d7f6373516cbcf3 +size 390144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..695c3c5eb317b6818c252c2b34d97caf4c223450 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c26282b81f43b210a03de8a607abcf9620bbea248ff13ead214503186e8e3db +size 398499 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..4d0177bae4087c9af0cb9aa0b256577127345e01 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--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_fccf2ddf2bf73205ff5e+be13b572/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d092b3b4dbfc63819770a5c31fc1a4d23c68c36c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa05b05dfd56c54c2f0dc084e7f6338cefc15e4f1795bee00d22202e4f2b99b +size 103181 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..75ae0f8b8a6fe502d092124dd1572d9cd5a69fc6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aa4e36eb1ba437a5fc4badc1129d56d094ba89ec9aaf22d06e28d000d77b10a +size 789504