diff --git a/.gitattributes b/.gitattributes index bd3a32436d84a0a6cd5d5df4485a05d68a980087..ed03e9b47d6514a6f5287bd0505d87f5207ec726 100644 --- a/.gitattributes +++ b/.gitattributes @@ -2450,3 +2450,20 @@ neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/wrapped_neff. neuronxcc-2.17.194.0+d312836f/MODULE_9d48665852815568ded9+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3744fb0ec890ed0ee45b.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3744fb0ec890ed0ee45b.json new file mode 100644 index 0000000000000000000000000000000000000000..ed0db082eceaf0608c19f13e8742a1d37da62c0b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3744fb0ec890ed0ee45b.json @@ -0,0 +1,51 @@ +{ + "_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": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/8ce05e932094a24524a2.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/8ce05e932094a24524a2.json new file mode 100644 index 0000000000000000000000000000000000000000..dc996f8ea765e5b59ca82f5554a315a5d75b7e80 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/8ce05e932094a24524a2.json @@ -0,0 +1,51 @@ +{ + "_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": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/a2054036498cf7febe73.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/a2054036498cf7febe73.json new file mode 100644 index 0000000000000000000000000000000000000000..77e87d06f86107f64b2ea8ee431371ecf557f7e7 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/a2054036498cf7febe73.json @@ -0,0 +1,51 @@ +{ + "_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": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/1db37f9b275c28f31a4c.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/1db37f9b275c28f31a4c.json new file mode 100644 index 0000000000000000000000000000000000000000..8f14d674cb985f92f7ed8166a71859ec90a79135 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/1db37f9b275c28f31a4c.json @@ -0,0 +1,55 @@ +{ + "_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": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/454a28c3ade838a69bb6.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/454a28c3ade838a69bb6.json new file mode 100644 index 0000000000000000000000000000000000000000..64d6877bfc3bd523c95f0af5e37944dc11e78dbf --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/454a28c3ade838a69bb6.json @@ -0,0 +1,55 @@ +{ + "_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": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/534c886df9d760cd4ee5.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/534c886df9d760cd4ee5.json new file mode 100644 index 0000000000000000000000000000000000000000..4e93e81d26c721758e6e730b75a9cf6f37e8cf97 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/534c886df9d760cd4ee5.json @@ -0,0 +1,55 @@ +{ + "_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": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/dacorvo/Mixtral-tiny/42dbcbe3264236b62e21.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/dacorvo/Mixtral-tiny/42dbcbe3264236b62e21.json new file mode 100644 index 0000000000000000000000000000000000000000..19eb1308731b4b8cad547cdb3e63dd0cde88768b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/dacorvo/Mixtral-tiny/42dbcbe3264236b62e21.json @@ -0,0 +1,73 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.17.194.0+d312836f", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.2.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/dacorvo/Mixtral-tiny/62410cde55b49f22ca2f.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/dacorvo/Mixtral-tiny/62410cde55b49f22ca2f.json new file mode 100644 index 0000000000000000000000000000000000000000..e8624fe2422cfe36c359263985892c7300d028f7 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/dacorvo/Mixtral-tiny/62410cde55b49f22ca2f.json @@ -0,0 +1,73 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.17.194.0+d312836f", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.2.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/dacorvo/Mixtral-tiny/a61f5b20450ca3689552.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/dacorvo/Mixtral-tiny/a61f5b20450ca3689552.json new file mode 100644 index 0000000000000000000000000000000000000000..e01bb39ddca328c3df4160ec1fdf5b6b817329df --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/dacorvo/Mixtral-tiny/a61f5b20450ca3689552.json @@ -0,0 +1,73 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.17.194.0+d312836f", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.2.0.dev5", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/phi3/yujiepan/phi-4-tiny-random/1f86d9b323d4de2f798c.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/phi3/yujiepan/phi-4-tiny-random/1f86d9b323d4de2f798c.json new file mode 100644 index 0000000000000000000000000000000000000000..9e1670bbaba7d790fd42e85e71d2b8917e378cca --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/phi3/yujiepan/phi-4-tiny-random/1f86d9b323d4de2f798c.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/phi3/yujiepan/phi-4-tiny-random/cb63b47e3227ecbd6006.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/phi3/yujiepan/phi-4-tiny-random/cb63b47e3227ecbd6006.json new file mode 100644 index 0000000000000000000000000000000000000000..516cee96cf5b9074126de3a3b8e0959b1a343913 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/phi3/yujiepan/phi-4-tiny-random/cb63b47e3227ecbd6006.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/phi3/yujiepan/phi-4-tiny-random/e96c051b6b9b4c77a743.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/phi3/yujiepan/phi-4-tiny-random/e96c051b6b9b4c77a743.json new file mode 100644 index 0000000000000000000000000000000000000000..20c5311defbec18c91cae9c0d58abfd97ada887b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/phi3/yujiepan/phi-4-tiny-random/e96c051b6b9b4c77a743.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/1f07aa27385a3bacc0ce.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/1f07aa27385a3bacc0ce.json new file mode 100644 index 0000000000000000000000000000000000000000..e5adc3705c1a2ed341dda3ce69ca43dd96ca97d8 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/1f07aa27385a3bacc0ce.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/a8eda1338b750cadb3a6.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/a8eda1338b750cadb3a6.json new file mode 100644 index 0000000000000000000000000000000000000000..c77e9686f89c049ed9027af62dfb806b5e175f81 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/a8eda1338b750cadb3a6.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/e14b78afc1fa5e13b44a.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/e14b78afc1fa5e13b44a.json new file mode 100644 index 0000000000000000000000000000000000000000..09a194686c07534005726c1fe75f170cdb4d0559 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/qwen2/yujiepan/qwen2.5-128k-tiny-random/e14b78afc1fa5e13b44a.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev5", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0672b5f56c1c30461234+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_0672b5f56c1c30461234+431f5505/model.neff index 19b74f99d7005f6baf16a7a958fbd178265724f9..0b4c2b55689cfd6dff700ea6c59b9c3dab6d6922 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_0672b5f56c1c30461234+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_0672b5f56c1c30461234+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_088cee8e523341202b27+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_088cee8e523341202b27+431f5505/model.neff index f3cbd0d0dce0fa8ef87d28cd3d3c5630e4f86d58..ec16d748f1392d208ad23d83ae75c10495bff447 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_088cee8e523341202b27+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_088cee8e523341202b27+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff index 641812c0acbfcb6909f3ae5fe7e5cec51be84d9d..3a233e2ad3cb140d9e21eca18c1c872dea4be789 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a42bde1cae14e2adb4b8c3626971bfda3749679e38c4d9ea4d5dbb5b993efa05 +oid sha256:104f51ab3675a23b89a21db5993a27e9a5eeb09867470734c4497617e146159f size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d26d776615893c63f9487ce93dab0bf854a7ebad --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54bcdec06d89d654845d062183036a3a4b545c119ab7f8bfcfcf806a54b9b35d +size 11183 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b9bb661af47fe0a6b9906e2eb1994f0e20820022 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f539c4d46bd7143bb99ab78bed121b4565d8bbb9b15cd5fb0d86fa42eabeac7 +size 103424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a6e893a25329ac961b2d4fa2caf8cafe1d96623c --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3978ae0dae4598ee8e9bbe8392fc2e7e13757206db58da945eeacc59ca5ff3de +size 21402 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2c32aebde28ce9c1888970a4ed8f719aa2a80084 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1b80b788e3a49498f963+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4017e0a785242f34f89ad69149e5db39b1a813f6c647b8b31659cc1f0868e99 +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..64b088be808a82d8c95848c4dcf500d4dc8de3ca --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89450bb664c81cdf16fe49daafa237c12c1cd71f5d8ddae84827db4a2eee340a +size 17475 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d6ee4d3e056a02793ca5ef725bf9517dc9c20d16 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1df250ef1cf7a7de560f+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd560af6819825c7e6f05303464c481e10d74ad257fc87de57528001c694afe +size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff index a6c2125777e9b41b8733e225c1f08b4d1d556da5..9bd5cc02345a38014c839255db8a26d874df54da 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:11b12164888b716b67ed46b93830fac4e43f9e7990378269f683e7ec2f468231 +oid sha256:d20351b22fb897e1f04a4638ab32aea1487833c6b89eca18339835ba2fe27093 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff index 4b62d991928279e3e6e34e08d11fedfeda3ecfa9..41d72af9a60fade143b3d441b219bb185e1e1ee2 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ead3ebbe1cf12b9c8188be09fee3b1fc68585260e8c7a4404c442657ba6a6055 +oid sha256:7c20e3490f8986d6c6745d61708f73050a5ed63c89abe7876449170ae3914ddc size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..892fab43157a43dc2f6c0bc74da09f06fb265ea9 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/compile_flags.json @@ -0,0 +1 @@ +"--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --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-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ce8ea8140ac57a6ca4658e102461acd68aa0aa91 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc90fd439316fffc61e3d8c3621617633a5cb8d08dda6c0736121c32054c76bf +size 68277 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8026db06bddc76b16b82740a6767b0e1993b329d --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b88ebb6d4762cb58b080eb10990ffb1777c6b5dc0aec53275fbe9a973c9fe294 +size 257024 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e3efef4c9c613692ea0a96d77dbffdbfd4968bed --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_284ddd1b388e504631b8+bfc62e4c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dce1d8a73f724c37e0b050e6aabdd2a403608d397273e8ab815bd28129ade55 +size 268322 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff index 572c441b23e7502539a9dde0710e3a2256671eb5..0bd0d0e80cd6724945c6e046d00746659483c45e 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c0c9cb5dd8f03f5a551d5e99cf274e04fe28815ccd3e879779a7516ce857332f +oid sha256:f8a1c8c7baf1dd72136b79095ec0210f7f7ea3d2a0aec460b4b0d187d2c2d03d size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff index 8384ed8aa805cf39d7a2da13700519c9597b0875..fd3efb0aba19623e1ebec383e907a966a0e538f7 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d6e35c0d2fdb8ebdf90b9435bc04029b89281e32ed2f251d8fc0c888721056ff +oid sha256:55d6ee114007d520d9c57754d8e1ea3a59eec00c4e6fa2f8168ded13fe644d38 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..336dd20dbbfca606c5506b057eb0c7f9827de046 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38184c632616d2476fe6e7794270c8a51ed09eccce54dfc80c4ee171068da566 +size 20501 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7b6e5c2bcdcd177b7a165d1caad8a1833680a0d7 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba2fd19607592f515c10a8c9aa2bc7fe0a7cfdb61286057096848075d43a85f1 +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff index d14409665e3c136fa4678a92c3d2125aab51e808..c43b3b1a4dfa6f50cca5c403c6b963b776f936ec 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7e8aa683c7d048770a00a8bc0e022488b1ab80ef008cc962d7d4d851eaad0943 +oid sha256:b956eaad5b3ff2e9453f6a41327cb43195efebec1d36ee916427be098eee31f6 size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..25004c872e032ad759a0e534e8728ec30c8027cc --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0df5d765518a8a37e232a30badf00c24949b6001eda6acdb60c55bbf974e1df +size 20644 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b093e52b1aab4e8476171ffd4adce9d148c41643 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:287a3588ce8935f52349c24164e47aa539bd56ee6df2ab77d46e95b3ee22d9c2 +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff index 9a7b44511149499b857ebb7ba97b3a9c0d3eed7b..ef05193042d614d403e3d9f4a3b408b149d259ea 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a123eb66616175b59767a873603b31410f8a6e1f11edbc2be8d877baa3164ebc +oid sha256:7f0b07361864dbb9075ea5b55536a3b994ae2afd864ff5545d540a4abcf2cafc size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8b1f7d7aab0bc821983bd1d38df4faf672d933bb --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2fb1e13c30d14bdf2a36c1c0b2efeca926d064a4e7ee7e668c6708a0d0e0ee +size 16631 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5d3f97e7ee959c5533c5c04a2fde8d59691a7213 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_51d9fed86504dfbff43c+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3149c0dbff0f466cd18a167e6e043d018273baf5052a70b152409896e9bdfb3 +size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5368928916623911b1f2+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_5368928916623911b1f2+bfe5714b/model.hlo_module.pb index ca18f79643c17be12440885b24ca13a83a84813e..febf93cd66f7c725be9f9482688c6e011707bbd4 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_5368928916623911b1f2+bfe5714b/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5368928916623911b1f2+bfe5714b/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0d0ffae83cd5de1473d83f2e7cc99778b46d17b5294fd6771cb15b924f63e789 +oid sha256:8abee4f2f59d915c77ace5d59ac6e2328bb6e874c9ca72f02e4135b40dd4d1be size 47194 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5368928916623911b1f2+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_5368928916623911b1f2+bfe5714b/model.neff index 4c260b91f5f5bf51b7516697e869ac35745ce3bb..7a42fbd8eda905686b0b718df7a0dfacca95a1ed 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_5368928916623911b1f2+bfe5714b/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5368928916623911b1f2+bfe5714b/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d8a6f31d06a967e0605add0a59526083df8e89d0eaed1f0652c7a5a23d2ce5f5 +oid sha256:403599404640a90fe81e336ced26f35356f7a935eeb39be5dcd3eac89f162301 size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64e6e60637f6811c5a60+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_64e6e60637f6811c5a60+bfe5714b/model.hlo_module.pb index 294b3d8acd2a7f62dea63bf67b0bad796cf6a9a2..35ac41f37b039568a8cbc781e6597f2d7f7edfb4 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_64e6e60637f6811c5a60+bfe5714b/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64e6e60637f6811c5a60+bfe5714b/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d05dfb434ac3afe697289a9630e20cec8959061e6d0244d2ca7dd42c498ce80e +oid sha256:e3f8d49a49e948fd58a00763e8da581ebeecc0278eb7a1abf2f8c6830f3c9ca7 size 80244 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64e6e60637f6811c5a60+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_64e6e60637f6811c5a60+bfe5714b/model.neff index 2e3cf8886bbfc1f7af32842437304909b23fe417..88589eec563a8d49eacce1576f1cc230e95bee74 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_64e6e60637f6811c5a60+bfe5714b/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64e6e60637f6811c5a60+bfe5714b/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1a17ff48da5d0a6299577ec66a90b74bba08ebf9a679661ab0f5438620793ef5 +oid sha256:f1a63707da04d8009f2ba56882b4a9f750461bbee2e5f9030072635ccc6bdda8 size 226304 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/model.hlo_module.pb index 974349d60930a207cac52bd2f422f188bf0cd00b..0c0b7a334f678f0e5d4acb34c166032136032183 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5f9610dec7ae63287ed558149e7f54cb819cf7c7ce9876aedc1b0931e3e76ea4 +oid sha256:c216197c7aae03e2860a7f1fe84edd3b2eeaa4cb809c5696d03509e85e27e11a size 80284 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/model.neff index b881d03cecead8525b5968da4cf55315b86ece27..30ec4a3299c4d2058ef1286a6cb14f1e82e666e6 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b620936c28987328afddcf4640fe4578dda072cb8e1f8b3179f47ade9a923609 +oid sha256:d7d7a5adcabd527badfa6922bb4fc896574c492ae0748a6a90c3506fb4054e15 size 236544 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/wrapped_neff.hlo index acdf9ec49499d24ba04c3e59fba8e3c951c5b6a9..3f598d7d225a8c50e43b7d4807d6dfc4a6d3ce67 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_75f61142a89fa888d71d+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:038fd23bda7aa7939f823eb0446c52833eefc4dedefdf94d22301cf30c4f7070 +oid sha256:69f7141a82e7b87c1ea4d20192f29a818db94c94f3fb1ab7992a8a06c4627a8b size 244319 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/model.hlo_module.pb index 7eedc45142d6eb0847737001c9e13e57f2a8f442..4ed54e8be41eaa82bc68841d4d9d35bb9aef1f95 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:361c93cf23b6c861204f434b6f4b680add2a341dcb521642f95ba99ad51408fe +oid sha256:ae55c7b4fafc583b6550436d75415825175812e90296d8f1b8004b78edc90e5b size 48045 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/model.neff index b880a5479f9900d38ab7b86043b7c904bae68545..525ce100376c03da90ffbfa9d70050ac549b4392 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f54cfcb9cd9b7550a597e2281ab355a7dd7da3e349151b415422ba5c9fd3e7cd +oid sha256:1ca62ffd479599cb9695b4f92e01c089e753495b27a3aeec124ce61a63c03c13 size 2356224 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/wrapped_neff.hlo index 670b72cefece981dc55b5e1878f6a2658bf5e376..e0d73f0599502498205e731413c86512d414ff65 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_788eb0c6a9b0ca759eca+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c120b74390719a05ce1d398d4507db96cc267dbd826310f08de08324b19611a5 +oid sha256:625ba7e80dabdb5d80f0ab44841d427b688729643e9aeb1aef92beee6df0a44a size 2364014 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7a4e910c3dbc7ccf8eb3+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_7a4e910c3dbc7ccf8eb3+613edded/model.neff index 0f47fd619be380d689c74c5d846b5702ab9390a4..4e51db534d06af992d24376a2e1e33a3fc908b21 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_7a4e910c3dbc7ccf8eb3+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7a4e910c3dbc7ccf8eb3+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e80dd4b636c1c07e1433626d50e1c4c27d1c17ee492c2f785c4736cb7250c630 +oid sha256:77b25fac21a2477bf552edf9ca6aebc91b51c043eaa7fdadd3b00886a72aaff2 size 29072384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff index 5d9c009b07f5dfb31bff65a0bcf72e0383ed777f..3562218d435083a9ac90a794318e6ae5dbbd49fd 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6bde780c100b51b09d30319c86f773d3fbf14341b69a1c79910d22e791f4a360 +oid sha256:3e888aa43d68dd17d8a2e6425673085c9bf287b06dfb07cbdd37af13015759b3 size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..561d229e401204468f750c517bd8496a6ab1ea00 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e7b848fd50ed1cc32978f64e4698cd1f10eaa9221bc9dc60316760a651d212 +size 24382 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..92989db15585bbf9ab05e92cd51d5f15f1f835d1 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8c063f8f288a908bf850+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca0de0953ce248253fdedd0742bb581867a5c190e69d0ae38290643a44dedb6c +size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff index 14d0fa172ba1e892a7a0ac89c8f222567704b2c7..c33bfa40c8cec10436696925d90c97d8288087fe 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e08e7f4c0985008f33e84dd2d5ea8e90e3a29d715a5ce5b9043d7e6c5e62c1a7 +oid sha256:92e21aa5950e02ef4f5cb0bb15b2c72bb3ab52cb2b08df8ceea51caac12ed808 size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_96404ade088398b2f3d5+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_96404ade088398b2f3d5+431f5505/model.neff index 82415664f1a7a2426757c8fb8679f74576f5a34c..b053bf2d6a5983514e1fe6630efc884d23b401c0 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_96404ade088398b2f3d5+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_96404ade088398b2f3d5+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9d48665852815568ded9+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9d48665852815568ded9+bfe5714b/model.hlo_module.pb index 565301a112c43c776865041527cb372dcda49ea4..27c0739ebcc7a80babde24afe2d59e5379bee455 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_9d48665852815568ded9+bfe5714b/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9d48665852815568ded9+bfe5714b/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dceeb7dd49382409a9411da04b550b2b7703c090618d8778959ff6624060325a +oid sha256:c4be8b3ed974bc7a4f0e22783bc285a31c6cc6e9829cceecce4d69696befab2d size 80244 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9d48665852815568ded9+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9d48665852815568ded9+bfe5714b/model.neff index 4897ff3d473797b1583a2125e1ae47aa24224717..2d390ec66c1122942133d24f65a0bbd8fec4b6c3 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_9d48665852815568ded9+bfe5714b/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9d48665852815568ded9+bfe5714b/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2703a655a98e6c0b80f77c69e9c7f9067c21931cd629b7b70e27dac8270ebf3f +oid sha256:7eb4995282101e4dd46d49d5e493d85839c705a15e62641cbda2007e271094f0 size 226304 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/model.hlo_module.pb index 9e6759a6665238a9df3e444decead547074ff8f9..d0694b8edd6139cf51574a56f00b02eed0d0767a 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a8c2ea4cc7a8e6c80169d0e98c6b723f5850a5b21b0ebfe4b239f171d610487e +oid sha256:39c3b9329104c2ec975f082b004a3db200509208a253bcbdff5b46f06fd5e32b size 80284 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/model.neff index b03eb4fe35b7e8334873f82cf26d4496c706a0fa..96f1bc8107443610cbb1efbcb4b0dd81d4afbe52 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1e7ee718e24df70b9e6ac412d43a459121ef084dda98a82934adf3f5aa681130 +oid sha256:5a44777d97cf993e5722eda218e17b13d555ff27c024c0952bcc89bc526f1f30 size 236544 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/wrapped_neff.hlo index 76b5ec2312bd6638371afd8e7a4d39c2f44b05ee..e3c665ffeb1a4ed0e24c88ad7ba501dd7718c58a 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a21bcdc4a770063da8b6+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4af63caec1c4d6a3e460d0d31056cddcc76ac1b45d4f985ab56fea5b95e06080 +oid sha256:c8b75d5f08eb598dfcd73a92954b34be95e402d6d332aad12834fab7e5c8cd90 size 244319 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ddedf8047e3cc2dfea1add455687ec2e59136ffd --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a18136a0c5ee2b3f80ccfefce5e2065c2a75c972cf3c7ab7a73d27f9f378cf2 +size 11183 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ebd3d563a4c847798a0ce2c64af70ddf4d222ea2 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36efce145688562b0282e7ef51a43f3dce3f4f7374733bd83ead4d3f8db13931 +size 103424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff index 97be81d8bf652bb131b0d0e25e7865887da2f6f0..7420a2cc06572a08e26b78246252491071684536 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a92b66243fdbbb690ec1d01e5040d773ed3419e3db662361b3e9a89a8318e9be +oid sha256:2eb60cb7e749593797f7592d265d0f9624eccf916ae74c891d6f86c71845ce55 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff index 1ec5872a4d02d08e0702fddcc45d5744a7b5779f..27a8ec0f30259f04c4b69621fc0b789617b4541a 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:02fb77b9a67238c2c03a8f0df225d2a883f2a7375ecfd0f1a5ec1f9bb794ba1b +oid sha256:a5d5d72f55cede7d9f840e9d12ee6d31b8a1091ea81c53727fc6b1824a8f49d2 size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..344d99d0624ebe8e1c04d8fd053d32bb8b18efcb --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97a3ff299b77d41425f3ddbf6b205847b1158cc20d89f1aea55c0f2d50e49dc0 +size 11183 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8058b70ad201cacb03df8e1c6cb5f4d1a2380300 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d8a29e71654f0529198c27232daa1cddfd5dea5c29d249af21df6a0e3c61331 +size 103424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a0369b589a88935d375ceae1e5505d6307ae21d4 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1716e6ab08c7d8828b58c7a4ac4fbd4cc7a6574e6db4932ffc53020aa28bb0 +size 19832 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..55e0f7ec8b69d72082c64d47ff9d48b0fafc7d7e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cf41a32ef696654dc19b+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e030f3d49ccdc1729e6f470b39b2ee25f4ac8236d75b80b3eae3c2d8d2c380 +size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..892fab43157a43dc2f6c0bc74da09f06fb265ea9 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/compile_flags.json @@ -0,0 +1 @@ +"--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --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-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..08ab27aba51a5348c03691831ab1f28c4edb4232 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae0ad2fdc6bac0e334b78d00b097e0bd9b9dd5ac6d4c56422df49dc386f92f4 +size 79431 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7617a9fdd04fe5e28ee0cfa6738a9bee6c6b460a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2dc1cd13f63d5609eae1c77ee53b11be787caeaf54b7f54db033d8d1f322af6 +size 318464 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fef48e41c2911add6bd160dd7ed7a2cfc35ef277 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d06255807e916c398b05+bfc62e4c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:309ca07a8bf522d53c4f961ca1f8dc782cbbf51c8d928ffee3c42456ed6de287 +size 329762 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff index 6308062db6569065815e32eae431edda3c082728..86bcf9168a43fdf0a4605cd2ad890d9ce0148ee7 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4cf53749f2b8afc799f5bdaa8c237022329ecd63b8622f85f1765270e6731500 +oid sha256:d0f6d84e6afa880313f964ac2446d89f0fc1b78557f0afb0ea4197a9149c9f79 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff index 592f4c49dbcee45ddc2a254ae304e55943850d9c..0ae39f09a133dda0463138c1b5936de27e3aae25 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:609f0d1ec94268f2ac566444a62bb480c29ecf3751265ea70843ba9d73eabe31 +oid sha256:400b052a3001b05fc5c17bd5cf499fcf80afbd17eb21e1f1b1f9f92effba8931 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff index 5e62365547a782ec902ae359c1bc871c447eeb8c..d988fc4f8a65db17e7ca5ae843b02d43536608fe 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:18083aacdb1651a6dec612800572786fd884c33deee8858ff5f602e4eb33f8de +oid sha256:ba5302b01ab44fb0bb3c86f3b9c0438d5f9d4be8f496501ed29ebb6ffdfb7923 size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..892fab43157a43dc2f6c0bc74da09f06fb265ea9 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/compile_flags.json @@ -0,0 +1 @@ +"--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --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-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..69c2d1f74b61e6da32c9d2a866dd2b90e8958636 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7534743372e1709951ddf865d8ac9e7fa5be14b954891c9ee8c5191fc3612fb +size 68279 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d83eb6b7ce0e0c3ebcc732680e2002fc2f6e93f0 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78e7110b0caf6ff75c769d70dc335952cc0de14bc70203a074e5f07db31895f8 +size 257024 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..8b1d7f39909e833cce68b6e03547f6c0e9ba0bef --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e36f587c697c4d8df3f6+bfc62e4c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:304f9357e737d61d31ede4544a89f80f334324c217a7d1b6d8a9a7b37c05e044 +size 268322 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff index 322c590a604851aff38544c1fc9c42f9ac1b2c60..0ed6ee6d9ce3be5b1170c30e70fcb0b1a5e9f5ef 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:715d0fc69f22f82a7f61cf83285c0928b7e66c9f2a7696fb695e09a6a9e78f3d +oid sha256:672217854cabd03e55889698c5f0dd1fb487e26626a77a309f2ec626d3996ab9 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f91cd98a64f373af274d+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_f91cd98a64f373af274d+613edded/model.neff index a3eee59199b4b3663c1e8d1dfe1e80dbd01c9db4..fd0d036eb2870740139b647e041ace93b5b877db 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_f91cd98a64f373af274d+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f91cd98a64f373af274d+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d67e5567b210909beac94e83b6f1552a1216d5fbc5f284b8e1118e5829351ca4 +oid sha256:966a2a187c166425a0ad14cc25edd340f3d0159e80efbc3175198080869029b6 size 2448384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff index d8aa651f52ba24d82f12d167858c9d997248c865..069decbe95dd02e639999ae6554463764de581bc 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cfdbfbe14cb15f43c04049261a5a9f55e990fa0666d2654ca060a423e3c2a797 +oid sha256:8886cbfbd5c73a8a5b45deda0c0311dd1083a4df5c082193a76d331ae08b146c size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9fa996af8937c49a5a5ceced87c69913aea681d5 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc82c7660e5291c3e6ff8e2d543a91c98d439a82ddfd9d72c6b94f879783aebf +size 16718 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9792227cb19ee6d7db0ae6c65ec21522f2feb8b1 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_fda7fb53c475ba393ed7+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466022d05cdac3a79f0b7868c2d020ca24ab3bb18ab425364307241b4b537125 +size 134144