diff --git a/.gitattributes b/.gitattributes index aa6507b802014e227be705720b2dd9d3d3054f97..626efcdcf9b7ebf43e9a346863f7446949b45c42 100644 --- a/.gitattributes +++ b/.gitattributes @@ -5980,3 +5980,49 @@ neuronxcc-2.22.12471.0+b4a00d10/MODULE_a0eeca96db30781301d6+519f203d/model.neff neuronxcc-2.22.12471.0+b4a00d10/MODULE_a4a4bab288905ceb01b4+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.22.12471.0+b4a00d10/MODULE_a4a4bab288905ceb01b4+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.22.12471.0+b4a00d10/MODULE_c841826784a9a062f620+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/ab85492dab47a880ba57.json b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/ab85492dab47a880ba57.json new file mode 100644 index 0000000000000000000000000000000000000000..c3f6a9a73df3ff3fea4b1c43ca92f2d7a34cd5ee --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/ab85492dab47a880ba57.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, + "dtype": "float32", + "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, + "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": "2.22.12471.0+b4a00d10", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama/llamafactory/tiny-random-Llama-3/5b1a29e1fc789f8196bc.json b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama/llamafactory/tiny-random-Llama-3/5b1a29e1fc789f8196bc.json new file mode 100644 index 0000000000000000000000000000000000000000..be152cb9114456907b7240c20753fac75be57ac4 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama/llamafactory/tiny-random-Llama-3/5b1a29e1fc789f8196bc.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.22.12471.0+b4a00d10", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/ef1d4a7a1638b14a3c76.json b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/ef1d4a7a1638b14a3c76.json new file mode 100644 index 0000000000000000000000000000000000000000..db327448cff80a66fc9d3548a9a8cf3d3db8970e --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/ef1d4a7a1638b14a3c76.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.22.12471.0+b4a00d10", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 5, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama4_text/tiny-random/llama-4/ce86a511276f84327102.json b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama4_text/tiny-random/llama-4/ce86a511276f84327102.json new file mode 100644 index 0000000000000000000000000000000000000000..586851e2f59dca4697bc3dfb57ce0554b04cd1a5 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/llama4_text/tiny-random/llama-4/ce86a511276f84327102.json @@ -0,0 +1,81 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "tiny-random/llama-4", + "_task": "text-generation", + "attention_bias": false, + "attention_chunk_size": 128, + "attention_dropout": 0.0, + "attn_scale": 0.1, + "attn_temperature_tuning": 4, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "floor_scale": 8192, + "for_llm_compressor": false, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "interleave_moe_layer_step": 2, + "intermediate_size": 64, + "intermediate_size_mlp": 128, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 1048576, + "model_type": "llama4_text", + "moe_layers": [ + 1, + 3 + ], + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tiny-random/llama-4", + "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.22.12471.0+b4a00d10", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layers": [ + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 1, + "num_experts_per_tok": 1, + "num_hidden_layers": 4, + "num_key_value_heads": 1, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "tie_word_embeddings": true, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 202048 +} \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/mixtral/dacorvo/Mixtral-tiny/1825ae490ebaf0066f3d.json b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/mixtral/dacorvo/Mixtral-tiny/1825ae490ebaf0066f3d.json new file mode 100644 index 0000000000000000000000000000000000000000..3f05b27a0fd79997a9bc1b07b5ce0583a35049ae --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/mixtral/dacorvo/Mixtral-tiny/1825ae490ebaf0066f3d.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "float16", + "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, + "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": "2.22.12471.0+b4a00d10", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/phi3/yujiepan/phi-4-tiny-random/0e9348e3d3a6c205f402.json b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/phi3/yujiepan/phi-4-tiny-random/0e9348e3d3a6c205f402.json new file mode 100644 index 0000000000000000000000000000000000000000..6ef06038f9f1ef7d5711708e646801657ca5fdd9 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/phi3/yujiepan/phi-4-tiny-random/0e9348e3d3a6c205f402.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "dtype": "bfloat16", + "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": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.22.12471.0+b4a00d10", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 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-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/ee6c482035b6b3473cab.json b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/ee6c482035b6b3473cab.json new file mode 100644 index 0000000000000000000000000000000000000000..7fea3c69dca5f7d930d5eb5c32d08bbd4955db88 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/ee6c482035b6b3473cab.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.22.12471.0+b4a00d10", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 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": null, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/a80d800541be4e880ee3.json b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/a80d800541be4e880ee3.json new file mode 100644 index 0000000000000000000000000000000000000000..29cfc20de1eaa01964a32b86b38cd8ac09cb87ec --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/a80d800541be4e880ee3.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, + "dtype": "float32", + "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, + "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": "2.22.12471.0+b4a00d10", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts": 8, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/1032fefb59c006443ae4.json b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/1032fefb59c006443ae4.json new file mode 100644 index 0000000000000000000000000000000000000000..b3c943dfc024dd1df227861430e2e3402ab82ca9 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/0_REGISTRY/0.4.4.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/1032fefb59c006443ae4.json @@ -0,0 +1,134 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.22.12471.0+b4a00d10", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0112aae994c0e5ee4ffb7964b455c10df844bb1b --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d73215d4780160e939de28250ad42b94508d35c2ba646fad8a9285fcb222b6 +size 315826 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a914b66c83ec74e52201accdf6427208a8677f6f --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a9fd3cc53ad834cff00d8719e1d6445c5424c57969cf4d2d8bf778064a86e3 +size 308224 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2aa46062565736ea265612f020f899fe3ce2b13f --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0734f7a73b49a760847f+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee357edc1ae39dde566b88e403a37b397dd8864e6ee6f99c0fe061fdc733293d +size 319618 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9b3da5a11f3bd7640110c44b14fd49b6d09629a9 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19d9b572dea8c7a7f1a70d2a2172b3b243b0a2c1cc1e3708705ba4805f245da5 +size 314544 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9e66682d17c474dadddf0ef989560ec8cd9ddfa1 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0797d0342f401d9572e847b455b1f792e1005edad48d868e0d4b5003eed324f0 +size 308224 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4edfc7df8610b49745380b9c8a4d63ec2e48d854 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_09867c424bfa84dfcf5a+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fedb630b868e7a2ea54040e6e615724cc44eebe43c42e645603ea64753fb31d +size 319618 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2136133e32335c540ee6230800551cac156a8f39 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f173e475a11e2a7955ecbd2fa78e024bfbafa4c64ac64322268e10b476cc3b2 +size 244814 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7a7382325843faa01e8c314847491d50fec8fe23 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0ab63364bcd05580a283+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe77e808f070091690bdaacfb27b7e4f8d94164ed16d0578b34f18e168b5a42 +size 287744 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5d03b7cdf04073a06521277b2353e0b829c29fd3 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8069af4ea562006fc223816842ec8f47bfa1d48b033fed0f7ddc3fcc1138ba42 +size 1147291 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..310775d1fc63d61847fca218e8efd22373f4a962 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dd76db8eda30b09a4d204962e945062469d08e2cc7cc7b7bb858adc107f6c9b +size 594944 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6c833ef31431045ca0674bc02d22a0eba01f7eb6 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0b667d06d984ae2415eb+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f84761431b16ca78119e709070be533518005e2d0f623da2c1ba7846b33ddfd5 +size 614445 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..c27e6c39a7a4c3b736e614d7725e8bfa29486eb1 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bdfbb08ebda9dcad199bfaa106a3d95c6f606c1f --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c78b43d7d485cdedc31104fdfd885a0a12552c14d2d2450f3f9375770c1073 +size 1783977 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8f1e4797253a002912f2f9a3fa8e3a9c9ded14e9 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_0f8f90687a1080fc3678+0788fa03/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:436ba50f0621abf64ea88297c63b219c0925b4b73cef49f22a78f97290016c7c +size 4035584 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2df555fab561ac4f8280e900c15e09b0f0dc23d2 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8a0b481dd3139ac500585132619c50a66dbf7dfd --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c57ef43047a70bae4b6a7176f61bcfadaa9beded533dba23db140e66505f077 +size 322952 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a2049ab0da2983e74bb14f6c2584df14209d9d25 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1389221757af9c7b1df7+b7ba88c2/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e0794c58deaa6bd3422b54f6085f439093af87ad2a9d631667e03518c8783a +size 441344 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ccb5b925e622f16c68624ad36b2e33938900d4c9 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc48ca1b2611b5ad051b02e8ed3b44dec07322e3b2300e6a2f995bd18f7ce921 +size 272727 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..71c03ba2d37d2d144653bcb91871b908435335ff --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e0296fbc87d52070801873ffd3be4cbbbd8a4600637354fcfe5b34110ee733 +size 308224 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..af286d45f6a7e734ec326f65c0e28c0c2dbe3865 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_167ee952f5ffde447542+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eab23b70063e6899f29dceee0d08b468e05508bdca3b3484723fb735fbb53e5 +size 316437 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..32ccfe0547354074aeeab099a1e84066413c3a74 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f8ba3e488ab72785cb4ddebbeeb2b227880b7f4be178aa092174ff8d0bf6dd +size 292043 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8c871a4d1ec6dd659c8c28c28b15ba7db6aafb62 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_1a2557c4b251a50a2c8a+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f7d975a1fa7926a7451e2a3cf83029efe1da26991b07aad45808b4c3a5fa03 +size 390144 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4ab56680fc69a129b8a69d2559c0ee0fca200b19 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b35fdb2007733da53c843e8e47518ba0b805f4480c4457363003876acf9470d +size 270365 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bffcb5a07847ad3f09c9908f67da1191e9489189 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828f1c6ad55f4992b0b53c0539040115cbf737a50e93220f9042adb7a3031d82 +size 277504 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..faeb1cd7a9550bb05783815c69c4598e86b13349 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_29d1245367829925f390+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35b2b115fc21de42317a455ba79c9495f55075553bded9b06352e6d5b7e094e9 +size 285687 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..607eeb5a45b40279c4420d4a47fbcd6ceed5fdf9 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40da482f53c37175a718ddd716b9380e2f6bfc07a24175b5c9fbd8f83355cfa9 +size 1184200 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f8338177ce7a05f1559f7a83463bbd9dd5524137 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_3d4b43665f1b1f693abb+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be0dc5eebde7bfa5a749381c0af5b50793905b2f0a50ebdf9973c4dd7bdc6c13 +size 4353024 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..36cd72c67d9fba238471f4524ebc8aedb2d299f8 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5a845237f88a46208caf1152811368d74f46fc2d74b9e7f9df9601772c1e36 +size 315844 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cebfffa8d4db2f629072238576d87bb26b87504d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6bc942fde4b04413f26943749fc96d18a27704ebd8f70a478e2c7e03872c56 +size 308224 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5df28d6d0425195c32b03bf84741dbaa079290f6 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_4632a636780e68814286+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55581762b93a765b5a1ff7414f86e338fd14f0b44bb07dd0f526dd078b3f1eed +size 319618 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2c5bd1b9fa266ea392b434ca695eff0daa80b6dd --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa482a6043e75eb465df0ab8a0e1df6647e268ef1cb14eb7da115d066be69ee2 +size 254818 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c8d126e535a45633e3e86413d82de4b5e5679d91 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_509c1a379916e29760a3+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6363b2266a53db94ed47aec529f2a3cc6a5a93c2a6e075333da066e4047bc69e +size 359424 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..4a2c6d0b18bdde36f52f4ed6e26438f684add83e --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..34fc8eb58f5af8530492f1c201a301932b7f3a1d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab75ce7a4409d2c6230bae33eb9d35ac9fb7d7308d3d833bf0222f4e72652b3c +size 303522 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..97fc21fc45df1712021dfc9108ae4935c45f8d30 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca0b8f588db25766018cb281503a83a346e6d69314c690a6a654fe7c01d83974 +size 400384 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a526fa158883c5f610933e055dde6bab75de785c --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59198f7736511b94f6e7+e2a39c39/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de73cfd485a2531baa08f24333c350e4837c88a69a29f6e3420be75d5a35cfe +size 409945 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..198140bcd39f9687ed3987fc8c0e5e5d8ad896bd --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b5c42a803126ccc8b748cdf4b84ef10a76db4dbf256f86e224f532441ce1236 +size 2980109 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1b8b4cebb8e0254e766667183674f4a503e78a1b --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_59b0dfe47acbb84fd629+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31a7991b13160f1850c1ef55b0ceb7e0b6bc9926a441f2b10e5416b5baa3b4e +size 12309504 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5de66d5c968111df0e686be69f1a86798211eb53 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ec4709f2d4dadbd658ddbabdd2dd22e4ccbdf1ef65cfa5b46ab612a557cf99 +size 292280 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f07b2f7c227659018687465a444425e3b7fafc5c --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5cb29fd67ef93662a5a0+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3a07c3c2ec4e99540af6a2ce784e8dee0f9d6b16b430ee0ab757f567e7bc53e +size 390144 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e0e73c7b39e87d4f20341c795a1630ca2c8ff951 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b95aa29b6ebfc37d1b81e4a1863346b86eba7d03d0e72020a93538911421174 +size 249415 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ec525ab4b5cac7cb3dc6fa3e153116053945b6e3 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3b0febcadf815e4ab09298284beb439fdf30811f3a12ed0b0b17ce07407963 +size 308224 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..005f670b65e18b90a9cefca8bebd7dfddc11cc94 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_5e143bd96278905e05e5+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be5dffd1564f7cbc47421aee059e37757a705aac23668973540e8be00ef62bb +size 316437 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..289ab4a4b0ff9546757a68ab7a324a7873b27b4c --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52af09f7c337606b65adbe882b5a516c6fb6d63203c8494fd67b50ddbf99f420 +size 260321 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..77d42b13dd7b65302a696fea225218da124c85fd --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e81cd515f7367378ed42414d2a7860518d4c29b9b75af7e2fdf44d0a78fe8441 +size 236544 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d9f7a4e2c999322280a265ae0b0a0692368b2f1c --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_75f7275becb21ddfde2a+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87db9ce59db60868400c353fec570cfb3db749cc0c8627caeba4e2d4c7d70ba +size 244755 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3d0b5997cad6d04d35d5505ffa4344f494965544 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:861e77c6ceb5bbe27deb2eb3073973da0598900fda524b87739a00a8bb4aa9c5 +size 3641899 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ad5da28f52555398bc39dbd422949e722ab38ea8 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81b9df471cf76387b928fe7228b1f2f17a13293e36ce46c11db1fd6cb18fba9c +size 5223424 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6a0b2c40547f5cf2ad0e15957badda43cd0f2431 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_842356c564eb183c4d65+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c0a14995cb8a75377d03a9579157f46f4d9da7530871d7aa8dbae6dc87f6a24 +size 5389948 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8f0326f5eb01a6856419bc9b6739aa4610a38228 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad943ee17368508c4dee452f99de5636e4ef5d7b7ffc2bed866962dd3e511e37 +size 1649914 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5ba6dfc7fe5a436021952779ccf5ba7f64aeb5c1 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ec9eceb12b5aaf7c3aa397899207f79d96b3dba186ab3732dabc54b5d6a637 +size 2110464 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..932b0299ad71ffa2cbe54617ca44f8b3ef314d65 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_92ac2881f9ca0f71d32e+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba41c9af6e7e5dfb440c43d74460c30fe9bc0ad88114c2cc5aaca9df66a0d8b +size 2203380 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c761abb4180bc03b767dfe4a9cb22b7783d507dd --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b8b06081845c532365dbb9f64a9c41f809cdf3301047cb44689e53d75f7584 +size 254876 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..abbe0edb38d94d92d1883c50e352502bb1b30ef2 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_97532c7ef5dc7e4f13a0+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5eb66e62d8d3c48380e989e606d8c7c5b83d1569d6e613f781171e1b8535d13 +size 359424 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e14beac4111fbe121aea07f31ad8a8ddab33bfc2 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b251c946c7a3cb5750c736af0fd59d22940b269d2c1d1958a97eadc9547de154 +size 291824 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..46b2b8689b553388b7b3c5a897812c94c668eb67 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a31af46e912d771cbdea+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb65b9fc550bf86d1f96545853689dc9657c912af7ef68edcc8327e657a24cf8 +size 390144 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1414030e270c9d3547f2a7c57a2604438445f91f --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1988f1ea9c451fbfc23aec17bf82a2b96672a681a1c4cc0a9fb3782ec3eb9107 +size 234397 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fd7d9cc3366eedd6d4be709bb64a2a0297412c79 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_a8c767775500acdd8e3a+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b78aadc5fd81908ec71510957d997e99247331d7d32e3289fe99d27cceb7ae5 +size 359424 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..56ac24bb87d86ac04549d0a25d2a8296ed4d28ca --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f571e152372f7ed7b2539d50b4ab8b6d83d201ba85034948d0dc7ff4026a5bfb +size 253885 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1f4c0d50e5e2be2d104fca48187ca44da5532384 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_afaedb2859b9ad9b9fb6+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:994cf68b5429c020a1b6d75cc9352750b8361e9752a3f348eb70b129ab2e77c1 +size 287744 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b9ccbea02df420d4fb3721b9680978be88a7c13f --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81afe07849cf513a564830bb1e49aa49244423f62695583e609b992f54901ae6 +size 290975 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..055f2ec89dc904f0c7fff004c33103148f7324d8 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_b2dc50dd0bb673c35a17+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129fdd0fb69a76dfc041ed9b00c8adf6d153f749bfb5d1f4f2fbe5c0194e8000 +size 390144 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a1e0bfb8c968191c2ee4b4e7748979c1a6cd56ae --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2a2164c8d2e9dc5ab4a42e2f3368e95af9135181f766b765742d7df37d43217 +size 272666 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a2198d31b3d7a2476a28df336735c53766ddb7c4 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a6c2362ae3f910110a81fa0defbf5088a99f4358a4d83853c5d9fb6a769d2f3 +size 308224 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6aa210a2b17269f411a35f287aec998741bdada2 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_bcae6a2eb9d69ea94ae6+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7e2935b93a7968d16d018087aec63278c1a21d15b570ec6d383165251fac8f5 +size 316437 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5c28e8882b049fd5293067813bd3615cbe5130b6 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..df64fbd248f81a7ad87259cd2424380831cde8fb --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d687f2813a25a6318cf491adc7b26911f21712772fffc803b77b1a71296419f +size 345064 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..24e2d4d15fb3f1f8ef471ae66f690b5daf29f1c9 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a847fbb09112c0bcffdb0f33a8946ce1c68e0829d9630757a7efe400a541dc91 +size 287744 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d1aee76adf2ea4a2e0309f3acfd5bda0553c133b --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c7960ef661d9d15cc8cc+ae2b3e2d/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e959e636776a3d46a30ef1ea37116a22ca5c38a842afdd3a656408f38702d827 +size 299674 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d30a642ee4ddf34be258f29a957a29ca97941350 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:994f7d08f09810fd2804e95d999f97c6850b285a920bf611684d14b0ce971df0 +size 316509 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..21294e2bae97b853a3a43909eaeb63c1b6cef4f4 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a888ec60b9bdf4c3764707813df70ef3e37fd6622f797e1d597561d4935c37 +size 308224 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c3abd5d2fe1de35347759cecc5e3f369ef55a762 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_c847e0791366b4c4b274+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d51f448024ca4380e1e1150a42d74c9333ccb61e8c99e227118b5fcc42d16a +size 319618 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..673b23a403f7ff441ca76af56f1a2d0dbeb7a7a0 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a8bc09e6555f22ecdc423a527d81108f8bec6ef2e7c5be61f4910f10b338d9b +size 1206009 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2c0df05681f5f3f1c10516d849745c4ec0f9790b --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_ced952ae43941164aa1a+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072cfceb4160022a719bfee0b966b3a5748d12831ba2b03e2edd3aa218b74a05 +size 687104 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..4c057daecdc0a5abf2a9f0b7e56c591ed15e347a --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a5afa66778d8d5675b08f099d4f7f5783bbd165c --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3e4da955389ac153f05c21b5fd11391ec666fd4211675bb609c3fb67132b3c +size 399072 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..232b0512ba8a2cd4e9598fe0f37d4132ac53624c --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_e6164d1cf3b338ef4f0c+d1c00e0b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4afcd3aeba540a87beb9c0b76dc0f25ddd879bb5d4509c0eed54718f107ab5d +size 666624 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4ef24a0dcd9fd28bc66a5fec609f875b4b7f5988 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b52854103db09429fdac40471abd637cd051594907348f2fe55fa53b43dd6fd +size 292280 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5b8d3ddbad4126aa98011c1946a83111bb5e8f78 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f44ea3026cb2ce9d2df7+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:423466f57c5eb0c8df47694604c839c24110611f5eaacb661331675ca4f19edc +size 390144 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/compile_flags.json b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/model.done b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/model.hlo_module.pb b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3140bcda852f21f9a59f7017f0c46bdbcafd8b91 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c48297d82f3f7d66ae04f2f9b94b5df6e33a4bd06ef5b71cd10ef49440c54c +size 315358 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/model.neff b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..92aa2378915bc67493a1a2fbb80c79ee447f8d7d --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd3ba5508e91c0031c082186270c4f56e74a0a9a315a21e79d154edb0b0155b7 +size 308224 diff --git a/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/wrapped_neff.hlo b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..8e70972280ecfa1c5297097d3014da4f9b1e30e7 --- /dev/null +++ b/neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45f48f1cc4d6c6df6209a23d0d77a61f3d13e303ecf273bb15b2cd22309eee3 +size 319618