diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/03ee1793b53b67fdba37.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/03ee1793b53b67fdba37.json new file mode 100644 index 0000000000000000000000000000000000000000..6fbdfdcaf4715e41b15ba1c0a59d49f572e6656c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/03ee1793b53b67fdba37.json @@ -0,0 +1,51 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/efcc0026ed5c762dea58.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/efcc0026ed5c762dea58.json new file mode 100644 index 0000000000000000000000000000000000000000..68d59a3f9d742fe2a3027d553406537a1e31b0af --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/efcc0026ed5c762dea58.json @@ -0,0 +1,51 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/fc73a2065c050db68b09.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/fc73a2065c050db68b09.json new file mode 100644 index 0000000000000000000000000000000000000000..e54bb7d37eda04a3877a8d036d63fc332909a81a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/fc73a2065c050db68b09.json @@ -0,0 +1,51 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/5065586e7517bebdaf8e.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/5065586e7517bebdaf8e.json new file mode 100644 index 0000000000000000000000000000000000000000..d925ada00736f3dff7c44775de8905f31c9ed5df --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/5065586e7517bebdaf8e.json @@ -0,0 +1,55 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/57d9938920b5709ceeeb.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/57d9938920b5709ceeeb.json new file mode 100644 index 0000000000000000000000000000000000000000..53d5f08379158d5eac8ed2e669357971f6224fda --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/57d9938920b5709ceeeb.json @@ -0,0 +1,55 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/6c7bb9378758475ee794.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/6c7bb9378758475ee794.json new file mode 100644 index 0000000000000000000000000000000000000000..2ad46adab8ab976a1db480acaa42826b0ec9c6b6 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/6c7bb9378758475ee794.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/81866c45c8d5288cbdef.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/81866c45c8d5288cbdef.json new file mode 100644 index 0000000000000000000000000000000000000000..cd2d758882a080430abe0872f57f4f9e94ab29dc --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/81866c45c8d5288cbdef.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/929f6cc6d81df5648af2.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/929f6cc6d81df5648af2.json new file mode 100644 index 0000000000000000000000000000000000000000..703109c1363a0a84751477c56b75b68c78d48381 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/929f6cc6d81df5648af2.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/e76a1f3ff1d37decab49.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/e76a1f3ff1d37decab49.json new file mode 100644 index 0000000000000000000000000000000000000000..17517e634b4bf4ea4bf0fc63b38e967dd2b929df --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/e76a1f3ff1d37decab49.json @@ -0,0 +1,55 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/unsloth/Llama-3.2-1B-Instruct/37ecc17a2362e0ea3fb1.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/unsloth/Llama-3.2-1B-Instruct/37ecc17a2362e0ea3fb1.json new file mode 100644 index 0000000000000000000000000000000000000000..9fe0d97409dd69df7850c192c22a25f2d968203a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/unsloth/Llama-3.2-1B-Instruct/37ecc17a2362e0ea3fb1.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/mixtral/dacorvo/Mixtral-tiny/48671ae7681a294bff2f.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/mixtral/dacorvo/Mixtral-tiny/48671ae7681a294bff2f.json new file mode 100644 index 0000000000000000000000000000000000000000..dd662f373f865246891e8ee7452c14e551e15664 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/mixtral/dacorvo/Mixtral-tiny/48671ae7681a294bff2f.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/mixtral/dacorvo/Mixtral-tiny/90d07ea993a4106ac65a.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/mixtral/dacorvo/Mixtral-tiny/90d07ea993a4106ac65a.json new file mode 100644 index 0000000000000000000000000000000000000000..ed84767b8b25a58d8588acebab4c7d97b346ee12 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/mixtral/dacorvo/Mixtral-tiny/90d07ea993a4106ac65a.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/mixtral/dacorvo/Mixtral-tiny/c8f95b53a594472481fe.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/mixtral/dacorvo/Mixtral-tiny/c8f95b53a594472481fe.json new file mode 100644 index 0000000000000000000000000000000000000000..bc2bbe1a52fd5b7b96573b33c5a029471926780e --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/mixtral/dacorvo/Mixtral-tiny/c8f95b53a594472481fe.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/1296bbdb99146d4b02ab.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/1296bbdb99146d4b02ab.json new file mode 100644 index 0000000000000000000000000000000000000000..3505ba212dc81746d2f486f69135def99bbfdd04 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/1296bbdb99146d4b02ab.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/3ff6ca2a20ded0c5571c.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/3ff6ca2a20ded0c5571c.json new file mode 100644 index 0000000000000000000000000000000000000000..1ae3e9c3c87673b4d3c7ac75deb8fd460b10399a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/3ff6ca2a20ded0c5571c.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/b58cade3d8d5aaed2b99.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/b58cade3d8d5aaed2b99.json new file mode 100644 index 0000000000000000000000000000000000000000..e1e68bd2787a2165dfb4414b225a4795719deaab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/b58cade3d8d5aaed2b99.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/6c77e99a6d0d386f0f92.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/6c77e99a6d0d386f0f92.json new file mode 100644 index 0000000000000000000000000000000000000000..8e619c38d8507c6a20c554de2e77a4510672df4d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/6c77e99a6d0d386f0f92.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/896327ccd70bcb0e1606.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/896327ccd70bcb0e1606.json new file mode 100644 index 0000000000000000000000000000000000000000..e81aae5dfbde353bd376bb550c3a933a8cf862e1 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/896327ccd70bcb0e1606.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/984a30e1f373fb27c61e.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/984a30e1f373fb27c61e.json new file mode 100644 index 0000000000000000000000000000000000000000..cb48c76c26e71fb5bf7e0c30bf648e923c6fc08d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/984a30e1f373fb27c61e.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.3.0.dev1", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.hlo_module.pb index c01f5e25808b48598a46a5952e76dab4de607083..4f5abc24103823597c46ddb7f7f091d225b8730b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:940d63493c5e24e852e93fd211ef389b1227d8cdbda0e5f60d4deb32479db79b +oid sha256:ca6707e24b81612b57e4fb439ffd77ed7a8e7464b09f782a6fbd4dd087ad261f size 80975 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.neff index febc9382030289afe0d4325a4202a60f23d94fc3..6ff00fa0498fac5ea066d3ad1075e85845125509 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:40a5b41908151f72aed02aeff1551d6172c274387a8a3a1769203344c9947102 +oid sha256:8207cd1aa055aea2f4e9bcf0a1b677720683d9b6e210f9a2c47c19fe07c741ec size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff index 4975ab39a01305b81f0e5d87eaf2354f34bbfd8a..f885cf9873bc7ddff376944030b7610ad18cd2d1 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3c2406019569308d46e4a6ac2e1f967e02d2e29931c70a282182498189b506df +oid sha256:712cc0564a70d624be4585d9d0bf9e6da48ba2ab344aaa46b3bc2b69d0fb65b2 size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff index b030373c8df0669b11c65a91cf22272803f35308..f14ab1968f1fb291e455a031605932137664d35a 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:54eafd37216e3155bbb19f9b10bda0d98486c7540f01429c4e55d0228ec7d487 +oid sha256:6ea7a800ae23210b77f9ca5af753770e7ce3f20cac52a5cbfb6308b2b316afc0 size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff index 52779edbd68040207ebeaa4ca221085da91e415c..b98543615d9c0a00a7e007c255fe706c3e7051d9 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2c955d1cb4e62cf39f55f735edf9848dd993afcf1f289cd9a3d5eb5abaeba1e0 +oid sha256:209ce50c4ff21f9cccf11aa6c3c9fe8b56a458b85f915ae726b9e6e618bc10e3 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff index 4c2f073ed2a5fc89ebec9accf949d38dde671e4c..41b29e27051f96c51a056eed8081ce10519fc67c 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:24e88de2456b73775725e8be2e2d673a068ccaeebf5c4954d3be97d97539b72c +oid sha256:4a8e5a4b5ae9b7430b8f1d4af36247bdecb527e16b6e3522e7bf1f8d598bdce2 size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb index cbdfddb6b4c29d4fdd76c19944f97fde69a666a5..6db9f5b59ec4c1cda75a3ec43e068a0497f00e1d 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:862a0c3cbaa7b7892a69f499f79a983d7850007fb3f3a804332b3619497b002b +oid sha256:f3ccb7b89f7123461216316af02734622aacbdaaf771430310b55142ec4a8f66 size 448722 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff index 682a04d0fde8e4a4fd9b8776b38a109313a487af..4113f2364e8fbbec0126d65fb08060399256ce9c 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:92e447adc7b251e6a456c38bee619cded3e494eabe5ad1f47e44a3b2b103a877 +oid sha256:f309ec2855b27f9f1c7e04499d51dc3a1acc033f86011ba5fa360d32b900575f size 32257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff index 1a9edd07aace1fc9a85a1c21fe0761452485c6d9..4060fde18f308e6569f0819ade31d5c731fa0f30 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:23b76029645f1de881afff4922f1ec5904c07f3f4f51ce59fd9525211144c873 +oid sha256:cdff629fd4875b4758c2e7689d06fbf4d3f6af10147990e2e59d23ae0306dc56 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff index 1f0a6b9f8e73ea436720d563e41c14cd1704ce7e..def3fca2ce82b0d8f6281184d86ed60ffe8a56ad 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:45ab2bbb5224185ad9fbc969770f2d85563af272d116c01ade65fa7bbef2bab2 +oid sha256:abf956fe48036d70745811da6e26b78a5cd0d05da19e7d450650ad9e91afb527 size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff index f40e3ba6eb1423a242e11aab691e07a3e3134fec..b4d040f1504997b32cc9022b33a46e8a84d2d9b6 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8ecd79bfa7bcb4554599b9a929ca2f9dd4288f2dd55882e70b90cfe824ce5671 +oid sha256:1d3b6d3a13fd959c5d03095ca331b2f52bb8e851678a6a6eff44dc1ac703dfed size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo index 55d8795499d73b8b544a1c16027ded82ae08c2bc..23058679daf1930378cefaacc3cf450ad3fc9064 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ab33d4561540008544d9d3f9722416e9e4628836df20e0f6727c92302a3ffe0a +oid sha256:38efd1d0e95256e32d7c73e4e8b3c7bd98e9a56871c84699c620d5cd1920e304 size 268322 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff index 640fbaa90e5ff4b9a9954957658c0511f68d1104..ffda26c7b5537289a41a77f2b432c4f1743de6f0 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:032778095a9af67c72696c928944d338fe0d7631f14707b692ad348377691c60 +oid sha256:c11f49ac265b6a8d5857e4bec676fc5ac5254e40aa32cc36531aabc2aee91214 size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff index 4020d449793791c2c66a0a86425e80a9e97f48dc..499b39bc923d97772e11d9e6ac189d834808ad2b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ff43ee8a129d30924ff9b3562bbd18130313581226e9677b542793d39037b07f +oid sha256:65de3b8fd9d7a5337eabaa7893537714a910ed599cb2ee67e59293f7a36da99e size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff index 31f7fd8525907af45e2c4732e99c066c5959e47f..bb97bc4b3c58b6124c84cbdf241f6baf403de2ac 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_34a6b42796c8b4e2f58b+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_34a6b42796c8b4e2f58b+431f5505/model.neff index fb5d60b38b16e27ad3024e6e8f794f0000d4bdf8..44005c7353fea4022a2e9c6e68db47684b751fdc 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_34a6b42796c8b4e2f58b+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_34a6b42796c8b4e2f58b+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e0d579312347183e39ad4ecc3e6ef0c730cda4cb4c6a01803cfe4d6e66774e16 +oid sha256:b93fabc1801093a09caea0fa761a39b924a9319556993ae785e20c78241e0f9c size 1158144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff index f0c459ac610a7c0816fb0d45c7beec44c50d9838..85c46ed059255ac03d0162fb686c831a12e5f134 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3b5953201258898d9bf0038ef63007b06ca5a622e2ce0ae14aff29150510327f +oid sha256:0d6aeb3f38b07b2fdcf6f2e680c0444d40989ae6046cbe947d6c8c1b38fcfa0a size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.neff index dc84b998ea94f856e26728266cacfddb226a9ad8..a92b08c95a3200ee9cb2653f957de7d034fb82b3 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:08faf8e44406b087550ae9c49d4ef877fcdba6c13140018f989f3ad939b34b89 +oid sha256:4537046a6a43824c15281096e8092df328725b74b4d983a7ce4a20d9eabe530f size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff index ca164bfa0eba9a1c9e2101344468013d733073dc..36ddf6b089037114d17c28fcee3cc48ea65f17e0 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:257dd149284f429d33e419d6fea0298c8961b7ec25e04772dc082cacbc243760 +oid sha256:af9bda725f1fb52ebbc3ccdb025ca435b68543fa8c8db4dfc4dc7550f56dcb40 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff index ad91641b210d41642e80acc05afeb688c10b0356..08ab7d9936d9ca14053bbc508353f55b472ba499 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3bbfb2ef58b084162e10490249888440a09e7265099f49b20e2c168d523f9721 +oid sha256:4c829e29b801ab1c55fa0203652e35021a92a3fb9764cfee430ea68a64ba1f56 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.neff index d71713b4556336461b066fbc1e184ec3221d53f8..58dbfa059e8e9147434bee91726068f29d91b04d 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:781b8b27ce00232acc6ea14e1c1ac2cb926d69e0453a1ea21fd1517deae13b4e +oid sha256:e53b8fb997dc2fcb8759f10a88c687593562cf6bf7bea98d9dd7858a0d508aa4 size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb index 2e793f62df3c9a5f1ee0b1786dbdd566ddc65fef..e6f33a43c33a80533ae73b0063d60e0daa09d1e9 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5fa7bb6da1ff6c9a4d1024e95303dbffef7b4210925cc91757a7428c02bbff16 +oid sha256:2f60b69002d5b5cc2b0e7d9c2da141c97b7b52df0a75908b882ce4a26aa4de3d size 47194 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff index 15e8969784f6814537f0805283e8810197c76c37..e925bac6777058475319c14ec24582e3fb1d868e 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:54f874a5471d91d2e953da4bfbe2a66a8574358f5707ad3d72a39e168730d866 +oid sha256:a19a5a0a62270b6eab7786a803cdc5049f57c2bd5ffe8dbcb3e4f3206ca569de size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb index a02cc458df77357968ac384dc77dfed46795b548..554172691e4746ec1d45d631383e57de7419ad66 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7a78a1835f3bc34db45679ed6e9d165ac4d2498361b4f20b53184a2bdbc17ebf +oid sha256:21cf5c027b34406011bdb0ac7ae8f0de44055c4bc5e4d2cecadbe543b63330e6 size 81317 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff index f4995b8aabe515b0cb881d2ef0d03dbba9c4b04f..e564bb0f9aaa17ac3852aab59d9c39abebeda572 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9a8afeb021d5617367faa20df382eefa0666ea762d5a1df90259af1f9bcc0d45 +oid sha256:f8609cb1efa5b4602fd283d7f2c3813a455452a9159ffa9b3616cdacb0919c42 size 359424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb index 54fba7fcf24fe55997333c666c6d7c206dbbc6f2..e3149e5049564e6472f7c5cafd04b6fe5dd62bfe 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:70523dfa46ac4527a2c01fb517d2b78287d79d278550f911d15a783348d7fcc0 +oid sha256:14a0969992856b5db95988762f04fb2bc9bb54bc6255fb2d71cd6740b2db743a size 81319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff index c96904d841834bd578acdc8c863f764f74062712..05b66c17cd7adcd9473145d641ff3781bf26ca8b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:adc381b8c686ee5ace4368e999d3626e9cfaf241e13d803f58f271c601088c9f +oid sha256:85bffa860c95571e7a070d4f956f9dd28b4b101676fc4316d73c4fe8be375606 size 359424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb index 9b980c2d035b61725160c2a9e1c2f7d2c59e8a0f..4db60a8b88042373b79cdd993f1f1a610c609a29 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9b7a7a2062b09b10f7f1d0769bf49855067b4bca35e9aa82f6076828879ea0f7 +oid sha256:e13cd93afd9d1e18b9ce7df8249f5d7d9b950369a162e113a1fc0bd765a22bb6 size 82168 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff index e5d7b10cea178929e8c5c8e7607d48839c20469a..29f06994f433f53e6a705abb326a6b1ca5e014f2 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:394271094cb2d742fd388aafd0e3ee83a274a9b0ff11a084f0f9c16316a6e542 +oid sha256:2032a8dc8a210e031f0abfcff0c1b170a94bd40cf549c20de09ac6211d1f3888 size 420864 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff index 76ccb608adbfa2a0152e7c2abc621382a316801b..0f2213af253814030b714c4488d79ce860044ca3 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:147853014224cbc7cf3e8b734afc60b9b7959c2f15d08ec0a2b2472bbfa75eaf +oid sha256:422fe9682a9a014ee444b66f45e6863666481346558b956507344d5b6e122b51 size 2386944 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo index 244915da5b2801839dbddec0d7569dfbcb7af241..47eb1b43377c0c550b1c1c3047b9a85144fffbfd 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dfbeae3bc8e69c9f4248160b6aa576552d407098cf4df09a8df262355c50cc0b +oid sha256:60bd55d6b3ed01569c8b1a01a8582321a55924ddcdac7f6da53906d5dde8d461 size 2394734 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff index 066870f323a51dca1d1c795e58bda461bfd8c1f0..f4a00541dc2e53694686c5511473532e2703ee41 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:739d2836b92b0f86d795152ea45e7808bcbc860d59b9f9f3db51b9e28fbc7a46 +oid sha256:4e8ea32da176f4dc8d6a274d7384d114614c951d0040f009cb040057800906e2 size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.neff index 38640ce74afcb0833c5954434a68c5d3b6dc95ca..6c15c5fd1439dbe4ea126030f03e7f8f69ed2228 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0748c8e084b158b202b301c0e3c3a8a1d2b891a564a87cb00fc9250b4e877e01 +oid sha256:074551c0d7a99069b4f2aca569a1cdff18aaaa79d1efc2971782f4421d2e1367 size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.neff index 47bb4b2ef8fe4342163f5491cfc81374a38c3ec4..57fc526d36d11d6472133c933a680dca121be116 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:52c1d9e5f2717169f958fa99ee5cea00712187694341ad1a29061f23e8b5787b +oid sha256:e464508dd627508dc80aca19c172c032b7b029605e03326c245dd0824fed4bda size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff index 4eddd8991b15c2c137790edbf67111dc4448ff41..8e3546cdd9c1b2e8cc07d24011e4672ae809ed7a 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff index bb59a8887a1e75702b8379269d4c58a6192c51c7..d487e3cd98b07f93516e28c7c1d7ab1d32704e13 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff index dd4da7170c9df99152cc1bc542059db583e45bf4..84767cb126d6ebb6302198baaa171f4099e34df2 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1289cc53f0e3dac59961968ae68e43e2dae98441db1897ba313cb027ca05e1a7 +oid sha256:dd0b75b70d9b38f565d8a4420f0c58f16d2a12530bd9592f5df427dd96bc832d size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo index 29268483c848456c6d981f2aacb90fc14c5ce5cb..f928416bdf194c0e8acf27f0393b9d17eb8c5316 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:37fbef15e62dab940aa9a22718cdf5d74f79105c792b47ee410cccb4258571d6 +oid sha256:51abd903bee527504afd2da5ed38f684860d8dda6d4ad0d10a46bb6bd5aab62c size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff index d5865495b9fca379b56c2ba09aeb1cde905b3a88..13c6a73a721cefa16c913ab78dedfb34753e362c 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:106b5d604040afe779363dc396979104e0f4630939494ea59dd10d27594db047 +oid sha256:f91acd2c97f470a43d376728262e11650397f0df0bd3e21b73cdabd31de30b73 size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b94c33a1002b2de0e6f0+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b94c33a1002b2de0e6f0+5be477de/model.neff index 04d37350007824cea16f14009b5b7bcf78d971e4..4a7cb7994f176c49ac18952c5ef0334a1819d7bd 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b94c33a1002b2de0e6f0+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b94c33a1002b2de0e6f0+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c1903569ae78d37715e5f8d11ebc5b24addba75be3a234f0214183d8a07bc0dd +oid sha256:13f01255ff3aa3270fa0b7fd38592e0918892fbe039b1ae13142314df31a53a6 size 4445184 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b94c33a1002b2de0e6f0+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b94c33a1002b2de0e6f0+5be477de/wrapped_neff.hlo index 00780a04d497d758b195d1efee2aab0819a46951..431f2ed8b0b961d4df530ec4bc8c7e53b034eb9b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b94c33a1002b2de0e6f0+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b94c33a1002b2de0e6f0+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9abb8316b56717215eda6d723ee785d74073d435832ffc9003ecfb6698cc08d4 +oid sha256:47f02a495b479ae615618d9c7d3f811d491bcc25f1c9e6192b469a6454889bd3 size 4514940 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff index a7d69f375dd6107d12cbd7c0a298871e65ce2cfd..3621ee740d0efc707727424bf66cc5433227fc0b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:73d0a18efe648561975b69d38af7585eb0c0e4fa9b7e27e99a15202a0d7eff15 +oid sha256:695b694bf51c1797551318aafa15e7dbec182256d41767cb48004bfcc52b15af size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo index 4a813ee6dc32fde436334c40ca37864c06a97cce..0111eafd372f76d58cfd001be27ed5e0d2a82226 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c4f1c0d429d458ac177c4bd9b7200f93fbe8cb8b87670bfe361df7c91daf0b71 +oid sha256:580bbfbbd38852325a66d43538d4af9a56264def563723b17119f32394787f00 size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff index 718f8bd136dfdac5932f584b1c9a046343f18bd5..98539ac03b7cbff158fae6c250c86ffc3f482bb9 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cbf9f8d57a03f1bac0ae367b13f554dc9c7478fe47e5a972c8d6a67732635d0e +oid sha256:62f2bdd3465cf29486d8331f5b914df5f8480fb845a381006194ccb306b3ad3b size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff index 6624cefec74df134ebc74ccea2df42bae49dd2f5..e1b25384d6de4b67836b3c0939be0eec9796de39 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bb6eb29b8892cfa37372bd38f3f0b1c0bed0e2440ef5be044a994fcf52cd30da +oid sha256:8e1debc545e71baaa12e13f9c363da725533421bcb8efaed5506f706cbc4454b size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff index 3847a339db8b97b3e0cfd99dcc89f34d43c88244..0044259d0c5316936c4b3976a90ccf69fa7b82b1 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cd5202d96bc9b62bc8619a0c47c805e25006b8e9747487762fb569778296d073 +oid sha256:a31825e68b433f96b8f27a06b40d31873d844fc3b0ba5a7ddfa394c01522eb6b size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.neff index 391a8b70972746889a37988b9f453449b101bc46..c069575b02e5e228a1573532ba036294dc1f2f55 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:435f7f735afa22c63f3a1d4f3948bad9ae7f3a721c48fe1222290ad2ad745b2a +oid sha256:cee76be438bdf17ae712d5cabbe867c3079988ea98e4bbae5e2d488d434fe97b size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff index c667ff8e5f1f5e3096994f03b4bbf9945030b3c5..0ce8006be97c9b7db1c0bdca2bb3e9b4ef5d4317 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2ddb5b2f664df99b34d78f03862e1d12ce902674446b1e83e3e8889c43d1bf78 +oid sha256:f5506215ed2cf2e22610ae66b87ace9a58d74eb949e45de19d83175241aa0a5e size 318464 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo index 10c7583e09ec28920c178fefb1477ab9f36e41de..3fd33b0a82dc0c41cb15fe38679cd93fe90dbd9a 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e99771bb94f3915bfe79d0f1de1176722a1da81bb8d2a190d05c41793d53eaac +oid sha256:5d5c629db0cd53a06d45bf70386a297e0e9590c758457bc6f5f5a7ae90093edf size 329762 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.neff index 9fb5529a8c9be0f154bfa402f1547a590c61d319..2758e54baab183275854d28057e2253c7f85f88e 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e49ece40766ca87e306279e678839317c0fd9f7504d557a43b558ba3b9115221 +oid sha256:750fbe7ac06d072b87c788c151a0d1880c9cd4909864c9068a19096ca219ec1f size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff index a551878664286549b9a3b23b05b505e3ebddc3aa..95564f7a338335f8c542f116952a2593d9766888 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:939153dcc0b4f1f803bd5737b5903aadbec23f1fba79df1ffe4c3207701a4747 +oid sha256:2fe3ecf644c5d79afa79ee9a1bdea288092db86be7aa7b690f70a6e06fd6ca2b size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.neff index d009c45e3d7565f7bb8706a1f3cb1e8e49670f61..cbd8da9efd6b7777bd7adffbce21157ddcd51459 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:125e81ea7b0ad94097c145088014c0362a663741b5baa17affe52b82011d27fb +oid sha256:69215cb61a5c9a43c14b4bb365fe8e677e195020903abff70be9d66a7f9fc37b size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff index 392f4599ac8a4c7bcfa10569fa6cd71ac70e1e23..e13e533343ad36f088f5e2d0fd3edd3808f6ce7b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f2d787acc44dfef535349a05944734726b166cd90a61980a6086e50715b27017 +oid sha256:49f1390a0d3f2d075f42832422d717eef5e2d74d352a8ef932e9239c315d4a04 size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo index cc6c7b5fd5bb18f80f52d60f9a1d23a4b6806c0e..77cff746acd6612262e3f8f63669bd4c2b4ba299 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:21b39155c9250d88fd5f95f789251805309df2c48ef76e697dcefce9546fa88f +oid sha256:0b59e4b13283beee396a66dee18720dd67878554a83c1ac8f7caf65f6e9b35b9 size 268322 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.hlo_module.pb index cfe3618f2eb8d315140022e76d83a635a14f4e04..1eb01c4127d118e9137ac87e4435772b3c8b8de2 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6908efe96eae9688ed6cf368a3011b2cf14d6d014cf6a9df424253966396ef5e +oid sha256:49d0dc98323171b756ccd9fa5fe72295fb0aff8b4499f9f7e106fb2ed583a13d size 80975 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.neff index b7676fb984f8adf69a18fda2693aebb1ea40c7ec..8c29b1ec43b37f60798673e30fbee8fad45e89f9 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:53b77dc392558fc18d230ef2b894c3a8b57cf844a4f2dcdb6379728b3d77ac8e +oid sha256:e8f9a1da4e087611a4b0c069434fbbf9438ae7baa36b4cc58f62bbc278c54eda size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff index 3c7a9cc202c0fc5c481f2bafa8b2fced7e3f5cd9..3158eaad3a6ea239bffccc8d4d3d713e54a5942d 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6fa967670b55e90a4f0f9017bc0708537a00a61458202d0dd000ec45843bd1b5 +oid sha256:2ddfd03122e7b43c9e79c7760964b12c678a8313fbfe0c3150be9dfa05ccc531 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.neff index b3102a76af7863703f249b718f2b399b92b50946..43289df644579662f81fb2f3ea742ce3756c43fb 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:627e99971985c6f3983d78ef200b3f713401dcf11a585f8a80c5da6d8ad3b74b +oid sha256:3d099505bed092b2ec91d116ed429f4687c0d2f0da79e2f29579b02cce8a954b size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff index 500f311aa397775ace324e129bb690fe6be3dc5b..4813a0c056e2bd7313ba1f1632797dcc8060e0f9 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a5936747a55881bb7dc5c04f2802097806055b84f58411b8c413d0ad6ed19b28 +oid sha256:f662a0387436c1e5132ba5487e2f12440e0d367aa87b52ad845fa81d7de4e9c7 size 134144