diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/0bb92f7dcc0e1d880913.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/0bb92f7dcc0e1d880913.json new file mode 100644 index 0000000000000000000000000000000000000000..a70e7a7a58658bb9a1efddd8471a8df31f897a3d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/0bb92f7dcc0e1d880913.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev3", + "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, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/248cb0f822d815a5cf90.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/248cb0f822d815a5cf90.json new file mode 100644 index 0000000000000000000000000000000000000000..9c9f3f63f952ddd355cf6a9bdb345d7cabd4ba39 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/248cb0f822d815a5cf90.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev3", + "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, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/6140d69dd6b8af37a79f.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/6140d69dd6b8af37a79f.json new file mode 100644 index 0000000000000000000000000000000000000000..93c682a2fb414c163e9ea3affe52444f25801b89 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/6140d69dd6b8af37a79f.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "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, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/830964f40b8e154d65f4.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/830964f40b8e154d65f4.json new file mode 100644 index 0000000000000000000000000000000000000000..a7d452c89908cf3a5367c44e20cc3de799cc842a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/830964f40b8e154d65f4.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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev3", + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/8eb55f88f85ca578bfcb.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/8eb55f88f85ca578bfcb.json new file mode 100644 index 0000000000000000000000000000000000000000..3af92c236cb7fe3ebeabcd8fae818e6ea16b8b88 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/8eb55f88f85ca578bfcb.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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/a8dae147d6e25037dbd8.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/a8dae147d6e25037dbd8.json new file mode 100644 index 0000000000000000000000000000000000000000..38e3d7279319879e54ee91056c171bf81ec74ccb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/a8dae147d6e25037dbd8.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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev3", + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/0984b1f74e21db9e1ffb.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/0984b1f74e21db9e1ffb.json new file mode 100644 index 0000000000000000000000000000000000000000..18e13ce6f21b86a92b96c1639f57d09f3550f95a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/0984b1f74e21db9e1ffb.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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/3ddb53f3c5ee3e669980.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/3ddb53f3c5ee3e669980.json new file mode 100644 index 0000000000000000000000000000000000000000..f127881eea024c3163f3933c60a253aed05f1db9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/3ddb53f3c5ee3e669980.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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/56d3c80ddad8ba400eeb.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/56d3c80ddad8ba400eeb.json new file mode 100644 index 0000000000000000000000000000000000000000..2b59e498e5f5b2591638c953f9912c43d2d914af --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/56d3c80ddad8ba400eeb.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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/da9d38e353da6077ee7e.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/da9d38e353da6077ee7e.json new file mode 100644 index 0000000000000000000000000000000000000000..56dc4a715e2e9d94eff156546b2c73334ab354cd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/da9d38e353da6077ee7e.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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/0d931bca7e2982964ac2.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/0d931bca7e2982964ac2.json new file mode 100644 index 0000000000000000000000000000000000000000..87c15d2cbbb5964394787d0ec417e0fd26ace6ef --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/0d931bca7e2982964ac2.json @@ -0,0 +1,74 @@ +{ + "_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": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "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": 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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/281c9fc41792d2036261.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/281c9fc41792d2036261.json new file mode 100644 index 0000000000000000000000000000000000000000..f4e2b62b55ea33df951af489a77de30fe6ec81ac --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/281c9fc41792d2036261.json @@ -0,0 +1,74 @@ +{ + "_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": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev3", + "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": 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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/9f57a5d3c69c0f48554f.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/9f57a5d3c69c0f48554f.json new file mode 100644 index 0000000000000000000000000000000000000000..3a0197e00dd14638a206b7d2a1acccadeef3e45a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/9f57a5d3c69c0f48554f.json @@ -0,0 +1,74 @@ +{ + "_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": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev3", + "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": 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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/04e512e8ed7a942e31bd.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/04e512e8ed7a942e31bd.json new file mode 100644 index 0000000000000000000000000000000000000000..634433e70c0f059cd64cab21f8d1f51d5e9d7522 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/04e512e8ed7a942e31bd.json @@ -0,0 +1,75 @@ +{ + "_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": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": true, + "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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev3", + "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": 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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/2144bf263e5e28d97f5e.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/2144bf263e5e28d97f5e.json new file mode 100644 index 0000000000000000000000000000000000000000..0c595d12e47a88c1ad28cf28423d73c31d4e8bb2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/2144bf263e5e28d97f5e.json @@ -0,0 +1,75 @@ +{ + "_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": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev3", + "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": 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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/7056308fc7427e647fc0.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/7056308fc7427e647fc0.json new file mode 100644 index 0000000000000000000000000000000000000000..dce97bded29e92ebb193b1c7951420c5bad24c79 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/7056308fc7427e647fc0.json @@ -0,0 +1,75 @@ +{ + "_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": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "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": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev3", + "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": 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-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.neff index a978b7c3d2899a1190213986ede5056215566c22..8e7dab0508df2c7584996c82f97470aeea26ce02 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_00333196986acf2eb79a+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.neff index 839a53667f3f4f343ea297c1cbe012c4264c7452..968a4ffd180e276fc6079a1a45a8304ce1f10212 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0661e1d8741e9ead0d5c+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff index 052a5fe066dbc0db1c032f62caa0c132e6d71ad7..56155a75859f7cf8a6f0a5bfb8359c124fa7cde5 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1ab9e2f02fa29415c2a584da7d3a0dd489fa46185414b6a6ceda1ff02a0b7e42 +oid sha256:5f82db1974675412b6b1b67fa058b2f2e17d3e8c1b1457222b62f3dd14357381 size 154624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo index 20944d74b5cd685ec7b965885660f201eb827749..3087e8d388351ebd5f2e50d3f4f7462ba9ed9a34 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:12294311aab65c8b1e1b69aefdf4cc623e27bd53029218381ec6a4cf66f7584c +oid sha256:41011885ae508e277133bd8db02dddfca5e88033b66dfd0a3fa1dbaddf68a68a size 162285 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.neff index 3d82017293d30b3ab28643e0391cf340c913f781..6b4567bb702ce3ced846014de535b0349f3c70ba 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a89157420d03816ac2f9222a89bce907177f1a5ca48f1137c20a533f8fdfb10a +oid sha256:513ef6ba9ef2cc12b54ca0465ab3613b3ec829e2918ee9ab362919c351e04a70 size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/wrapped_neff.hlo index 66e566163971ea284cc8f027409911616b1e7982..d0df79c9b5f6ac02e03a7dac86a714815dd2bc3a 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0f82fe03a3af29dff8f6+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f02bf62809adc55ce64637129b796e84a3032d0036f542bf94e0f21ec5512b0e +oid sha256:13a396dbbc92b2cfea1e81a1aa99169e1af8f4824411e2064cb6bf310908214e size 244319 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.neff index 011b0d7fda00e58143e76644f75ef7ee615644b2..879e442e3ad5c108885e854f809f89b638c5f23b 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1d687728a717f87883ca+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7620edb3b2c01abe336f904cd409b85732204a2bfa44a10ccba787a4a0b474e7 +oid sha256:eab365fa91b8f63af2c622ee0d752f23ef48d8510233402442c0f04b56dc0004 size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.hlo_module.pb index 07ea5de8d4ec025011e713c79a814335038dc333..9895d74b49d9c1a47a3e07a13817d8f5a7b77c7f 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bb3f3c80a1f760b0f801aa56dd94adcd18f8703faf4fbe1cf4629086b0f3ced2 +oid sha256:b38ed6f547fa42be27ce9362af398a0e272392b2773376e170113c85391ef244 size 87785 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.neff index 742722e53f4fd051a3749048f32e1f71c0a5aafd..9763ab5d1df746d10ec553905289062c9a16c09f 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1ea7c53c16e767166083+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7bcc37564d8330894550bcd1c560c819f27452fc9a2dccfc5012d25347f52f7d +oid sha256:cd3758dfd0d4000ee8975d5cf8ed77982844341ac5de32dc3062059968263f72 size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.neff index 46bf13757be27f687533bbe52663054aa1449305..643e3be51d06aa4bbc4955186ccbd2d2c8094e61 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8c09b60673a5f6626e5e43ee91b19cdf385f2dc3113114ba3212f31b086f1fc7 +oid sha256:bed91265b80c14fa432674eee5f400d09f5c4720716631b49db943797028caa4 size 216064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/wrapped_neff.hlo index aa33d546563690ed627a67157abce1c79029e277..179c16e0e88d1c466d2f58f99291c7844376ba66 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2371c90829406a620831+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6979a724da90b05c60b1f6049e232b513dd03d8d1a531e9c0704643c8ca737ab +oid sha256:5d763958c91bd933f00358a33b0fa4f5a65f6103349e5c59d663cfa41b120cfa size 223770 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.neff index 05d17b15f3dde62ddbeb6352d704c4fa97d8d9f4..2821e29340c5f4f96b69f857cc5fdb116e72fd24 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_266c5c386fd48dd67015+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.hlo_module.pb index 74f4328c100742b54a0da08568c623fdb58bf8d8..8bb40c75bb2f40dfc005dd4d4f6eefeefd76bccb 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:291711a5dd69387c68f5d90c715f4279533a4c872e22ca0cf368e4e452231d49 +oid sha256:a103450ab33c864fbb55eacd87a88a2e67d15d36e161525081229b013718103a size 81323 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.neff index a0f98f0612db6bf34905e5bd353636651630cea8..c66bc5d1f3a3fbdcaa7f6a6136db193b518f17c1 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2af3b88e8bfa7573c510+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:21068e94ed15da4166d08503c40bbfa65fb0b048bb3ee873fde12b233f4ae681 +oid sha256:cbad7d44500849fd06f1a8daf5488fae4b3ccb0758fe466e2ea8f89c990c527f size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff index 02623580a92f2986a82d058e771cb3d0a5146d8d..528797885a23d29bbfe18bf69e60a018e306fce4 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f01ec781276063d1550d6620dffe2d414e727480955959ac21331622c17ccf53 +oid sha256:00e95b6b76e55f22c6b409cc5944018414950ea113f3acf3cc8a562282f1f888 size 164864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo index c405456691ce1123c5dd9b686c63ac696cd4efbc..3035d31814e1c83df221419f7333af63a4520502 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bf1d4d6bdee08e32a94cb51eb0d019d7f562f7dc69546a7cba310828a021e389 +oid sha256:a8c908b58b2fa0c833312043f4cb411ce014dfb02884dfa59632073fee661478 size 172461 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.neff index 1454977989c2fa71c93b44467908fbb896400e21..31128edeec37cf9e550a95a60aff3400da681b53 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b878f811b89114a743+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb index 357a09cc68ca787b762d016946e1b412289ddb34..f41da7ea2becd56f076143c82684376bccd8069c 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:785ffb37d0114be58bbff93596d1905917de36982edf639ad3f6b98cd5e43415 +oid sha256:33216fc58955f8fe57f80a74b791f7a952c27bb48b72634961f0f14ec22364b4 size 82573 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff index 36c8e8e483c611c945a8f4104c982de48893bf5a..10b9ae8a6d9cc62683b80726afd9d244df42ac27 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f2aafae91ecad0ad9b888bcb669b64acb2929ce33065e9452bddf2d2d8ee4a14 +oid sha256:f79d8fb64008045a0ebb001572d4df02168e739997c5bcd168827c0cd9c5de73 size 359424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.neff index 168e202205361dde465a8b78023a14daa268811b..f579b2e43594bcbbcd3cc4400d79ceaf2bd3c3dc 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_39930d0c2120289c9c3e+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.neff index 2ffad384663ce2da0b032949452d86872fafabd3..51716ab3778f0ea0e6f906339f6e6320502c67a1 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_40b0c067485074fdf48a+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff index 692bc10dec58b206ccaa112ae651dcbb650b3cd6..bd7304b5d4249353741af3d9675a06e89254c078 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:82b6371144cf9c14b0241c348d02996e5997df9694353a59d7657009aa4a0626 +oid sha256:81e875c3da94092f70c3fe52f1409582678c44455db3a160085aa4c5ab348205 size 1168384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.neff index 95dc9d108b7a7133bb92bd1cdbbd17fb92ff31db..62e7f5cea30411dee053e3613fcdbe6b794cba6f 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4c948ba1d275cea9b124+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.hlo_module.pb index 2125dd117f8003a3eb43d47d4ebaf3b89e2a2059..f3dbc979822279068f33af3224a44965397f27b2 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e8dc89c6b2f228783a4b7a847c419d01d23623bb1c36c7346580d9b8f877269f +oid sha256:b8688c9e2cf721d51397614b2e076339014bae9f084c4dec81b4767ebff17c0a size 456914 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.neff index fd3f30a45f7c18cf8857511196d8e984c32d92c4..44318274d6d484239c1ead4f3f9a38bca393ce8f 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_51d7ba87477561ddf31e+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8e6440704e13e17efd6a9115b3ee8306b3906f06fc8106d08f762dedfc26408e +oid sha256:435545b6759d5fb3c8965ad4e3ece73ad59a5ebab6e7ca8c166ef90626646b3f size 31376384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.neff index bd52c653d8f5762e01ade9ed2f069497869146b8..d98ac4a2d734352791b12604cd810ac8b914ae08 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:39311f8dea15b407c7820c48887e5274479782b917cc9281bbd0f759f206ba83 +oid sha256:eb9531f7d49e162cff27a38c3ff768ba93f5c40843970f2a358c8c15d4221987 size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo index d6a9f07914f6426dd66dd4a1b5c8d4772d0bb0d4..5752a4cdcea55dcebc3a18d508080d41bef0fd8d 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dd188af2314d5a7eff13ea15abc949171cd513fc3e3d699549f36bf39dd1fa32 +oid sha256:af6ec3592d7652bee81a6deb57bb6d17749889558603aeb6b6b87ae6fc73f3f6 size 195507 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.neff index 0fe22e64e38d1b291a4c4719e59494e661f54328..613afac96ed5e58ebd0670a150e17cc8bcb85f61 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4bc6d1bcffc98a707063849584bd777524ab16d99a9b36f43a0c97a8b85341cb +oid sha256:a026dde85faae4f9d3cb9b0ded5eef48202833c49e9ba9a679068ade6b649405 size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/wrapped_neff.hlo index 91def0f685533e6ba7591af6311eedf398f790eb..1eba5e2f09f6b36915e7337131f16c42458d7c9c 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_67377aec01dd303d63ef+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4dee33a8f0104c3005b67b596d1d3ef787e7cd23850f1ffac3bde7c6b31e3c85 +oid sha256:885f35376078f8c68343719e8552a94d1216b5ea5c121092be7f11463825e65a size 244319 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.hlo_module.pb index 6018009af437dee58def76e11803ee14b43862eb..1e7cb06820dd9d58f317bc2ad0f2c0b8cbd80d15 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8595de39b60526028c04b4c6d00125d4521ba64bce786cf02368b76977ffdad0 +oid sha256:e6d2ff31344c4e18f93df66bf71f0e0031e7a330f0f1a0da2f851d8df0397053 size 50076 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.neff index a989d8e45cdf8d4232e0c3fd3460bf86d69be29a..dfbb2cbda9abf0c891eba0c8d5f279c6325d908b 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_679852c8ccd2cff92dd1+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:69ff807748f08a32821febafa966cdfe8ba5def5c664d1c6d02826fd2ee94358 +oid sha256:35e01f5762fcdc5c350f8e640e8624181cd7e09f5624d54528ee820ffe4f9729 size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.hlo_module.pb index f6f45609d733e98fa628e247cbf4f4c64040b3ec..539872c6c221bee7d51d24110adc5557f3864385 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3911b9e19624e2d62f7d180667f966981db8d75fba37e5f97e83efb5bfe119da +oid sha256:ab3b3149ae245870142e8624a7e42a3d7ebb217301b7894bf581bb52ff654200 size 87785 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.neff index 55268d0057a121cd68028b5e0ae16ca474cd9c64..29653c390b1f46383a31aeb6d1246f29c538cc71 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_761b3c734083fe56af68+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3a1d3978e4569f994a020271ae0831bc5643a917923e45b4c3348aed583775f4 +oid sha256:f941b8626f8e4846ac660b57f5196168180ff85deb7d8345bae8bde5fac21a91 size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.hlo_module.pb index 1627088221d0fa812c4a968a72bc1273c515f7fb..c07613336fdc3ceaeb7e6a409a39bbfc8e385911 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:65b142d87d876dee57b5b66d54c21bf5a9bc73b3d63a32d4ffd01c46fe2c82e2 +oid sha256:9963d065524af5f61615462da978f8c1ccd191354f5e7cf2e8ac27ba6d145204 size 80469 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.neff index 721c228ab64a1572b175cb9581b751dad03b08f3..051e6b3608350fb5fb24c6be28e4b8d9e26381b6 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7850f8c16172e0c763cf+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fc5cb8e6b7db67bf40c1e0170697533b941b247d1324c5fc287abf11640081c4 +oid sha256:ffb754e12ebdce70ae4291adad13ce17813f7db8d1cb7d9c3b65a4128ce46423 size 205824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.neff index 72ee4ab9b23d858eacb53ec76014f8351f2bb05b..460f01f9cd2fe1e234e8b4ce36e9c4baf3fe9631 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d0224d883f8020fbb8be6d472705c13d81bf4f3f1a27ad3bda24aa3146372572 +oid sha256:d628e0ed57be442af28f050e720ff85541d77b59481c553d2aba35c8d1757202 size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/wrapped_neff.hlo index ab3fffdfed99a4ac8d5d16069e703fa9e8f45088..898e6f1919a42635167017dd710dfbbeef0776b1 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_791f80da2052a6cfa05d+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:eaf33660ad2b95a5db5021c668111bd025d45020cf0a23ccf8fc049154b661ea +oid sha256:e694cc58f40e21e8ee79106b115e5fde2a45a256b367569b11130f750e06d880 size 193114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff index 1610224b254f298cf5f0e598b58480b909b2701e..1c7e49fc83c9e7cb4b858148ae5f3a08cb67a161 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb index 2d16df4d61f7ec5889998b2629acc4d936367f1e..709158eeb73366d694cd90d06703a31e54f292ee 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f61eab86b4c8d3ff91c00c1739d222c4ed2b688e4625c4bd8cda0e80dd81d38b +oid sha256:ef0c42404e937d9fafde6823f190f5bec7505e8ede91a070b000494ceb0d9404 size 83368 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff index f84dbe31ca5f0e7ee9964afc1d5c138ed65435d0..45d621b4a21ba3ae70a9b8f3e1fd93488f998845 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a833e92f3439f4b0359cb62519c02c51dda934079f1cf31e8ec2b8fb2f091c51 +oid sha256:170cb8932c2b22f2c8ebd63d3017f38d091946e6813b5b8a8522f644b30578cd size 420864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.hlo_module.pb index b3e09794147aa46cb3586f8df0df755a69e7d0b8..2df7b49190948421550e1cdc3343b5454d029175 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b8c3291c3028b7cc44e790e359a20c4a356dc8317135a8920091635dc195987e +oid sha256:500a453fcb3bc2deb600afcf4bdbc2e0b22ac4ff0acb59b7e8aaacf458868027 size 53803 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.neff index c9f55811dc28e3c37363b9de0fa5c277e5e69327..a80567ce4552426314228e6fe3b93f9b3f9e0439 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_81e0fb8dfd58e42d4ea8+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f04718f2195a2c1b43c763d1c97db3bdca3078632c6d0f8a05ee89c442b6f708 +oid sha256:18a5053c497b991c4d9817a1a96e26b5c4491170005bf53fe32f6bd7d6535033 size 164864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.neff index dc0ab807fa4ed801936b627edbda12c79d239e49..ad9333cdc4062c89ba8c04324b83a42065160bc9 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4041dffc23fbfabef08cc959c1cd21aed5b8ad5b9ac0dad1a8a4cb6faba17fe9 +oid sha256:564c01fccb7928cdbf3eacf9dcb6621196bbe00c553fc45581970f757eb81db1 size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/wrapped_neff.hlo index 8a814d634dfa89551774d83bcfc3c116ebeb0a85..743ced9b4242cfdae7a5f8321bf659fcc767f5eb 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8bbedb082fb6a65e221e+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e7962dec34318c62eafebbb03c003a1515a174f5348826c9b222ff2d8e3947dc +oid sha256:915b315f1bba41c268c87e09ae0da5ebdc5ee872dfc1e54aaf09bdc7d89e1ee4 size 193114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff index bf4c14732768a50c46be5b0cf9124efe046b04e1..cbfa714173e9d34314bb7f73e8cbc2c47641a3cd 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb index ac1c1cbdeb45a22e8c938abfda2a718eb2f8ca82..87cc519f48ebf4c34250bcd4e344b8800202ffa8 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9ba6755f76044cc182adbd3f58b2f88e3647ebe64d521e294bee38f33cd7d099 +oid sha256:e151a9d0604c5c332b0bdf11258b1231f2d64e253dacdc486ae0c7694dfdcc67 size 82571 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff index 7a7036c035482c95fe179591398f40ab70c3844a..961488751e95955332a17c66d1cad06cd0cfb07b 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:67ed7c62c7882a05f20a82c1070ccebd3b96ebccab601e9985d0d9d470ae03a2 +oid sha256:6b8ad8644a3be96b27a5536f691c13a4f745448e23627443024f66ac3b16b278 size 359424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.hlo_module.pb index 1654cfc00a632ac0cb2fcf75f4d89dd2d5d75c8a..2b98906299a2004b189371c63aa526122e5d260b 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:15a1f8e05a86a5c8f515e1c034a06442d19fdc3f1674c0fbf0e3499011b528c3 +oid sha256:3ded695006854713211c608a283bad16dc17ccb4674c1a4b5885a027aa80df7a size 83920 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.neff index 21da0c1439b8cfc9b6a7039588fbd4d8c7a400b9..3963698252270ade4fb4dd78700b3eb6bf92eb89 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d325789026e6ce273ae+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7d25a3804d66b7ff656ecf5199d0baded3622f17e660ef4f4736e8734c1b0938 +oid sha256:d37aec282d4e86ad406215bea40ef98c4a3cce24bc3087a14a281f325434cf25 size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.neff index fa00256331c0cabf14d56a463c8d19d3b5f962d5..1c75e7d6d1c6f240d121f00c9afffd916ede0adb 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dbf462cdeb496241af30d672b2e4f91b7541fd490d67691bee195c614e1fcf79 +oid sha256:b8b852f9eb66933204e2eea31fbaeb45e1bb9d20e4b303cb03e2c2745c8bcd93 size 308224 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/wrapped_neff.hlo index f767a06770c98dc1cce417af3b62edc988cb0a19..c0b28419af17bade65426f5603bc763a9ea31766 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e2025b598171192a3d4+ca355898/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7f4b338c58fc56e5397fbe8016b2b3780f5a925cafeeb733a1e0554aae0c5e48 +oid sha256:ccd7ccbf5f82ec51b3939615fb3bb817b8e7ed38dbc173a9b64c3259ec8c92b0 size 319522 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.hlo_module.pb index bae7532e62f87dd96aeaa2c2011979cf73338534..6e0dcfc315dbfadd0638ebff06bd903598c9b06d 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:44b160039d090f8d029b08fb98b9ef3a9477eb4389b4b08b4410dd67a09e9af6 +oid sha256:c507fa981062f3a00d34ba2358bf590e1e3a32f0607abaed1906ce08a9cbb871 size 80469 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.neff index a1a861c4ace0aafa314e00c9e59e651a373e19b5..a047b4c840bf27be803b3a4de5725b86b003ec57 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a1746e7481045e1ccc37+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4972af6f4c52b9f9229ad3866e5d54a272391a1839aafc8054159655bcad7619 +oid sha256:f3cb7500c0a510e8f247380aa565cd36eae4109ad4036427e9bdd82876b7dde2 size 205824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.neff index c15965095c8cba5111015087b355d4641c3a756c..7c7caa2384863f7c206aae532c63ceaf58265eb4 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ac1f5e0c4b538ef4d33b7c9c03dd4d8c636770d739a6395af324e36dc2a9fedb +oid sha256:e64abfcb506f2c17d5ab3ced2741d6d3e2d5770fe36f5c14685ce50c54cd66f8 size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/wrapped_neff.hlo index 99896f8625b657e4bed8991e55de90449186f481..aa6111e126394e5227e0270dbb613c036a027fd3 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a20343aa93b3e4cbf95f+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c7e47c8d6011c2921e8cb2c32b61ce263b5c06e42a22d81ade3f0e63d0c49776 +oid sha256:4bf3d566075f2caf31c91bcaf2851297454fc0c593d53457024d24d69d6edf9f size 247153 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.neff index 089d2fe0f250f49558924ccb8fdf25d122a634bd..6f776762247f512181001c8007d2c70dcb549271 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a963e9aa5a33fdf44b01+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:01b6e95760b38f249119c0916517c0021346d8c7908b5566fffa0ccb5067cd11 +oid sha256:3fd225ee17023e37cdd6559c7a6ff5e8089ba562ea13b88186eb50dcbc85234a size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.hlo_module.pb index b4e6c16f42b5841a3b416a34149ff1004ecb23d9..06d2fb00b0df45f843ea7f1d613d92a48e05c39f 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:78e4287bfc92bf850eea4d10461af2352f2edc23a29ebe6782591e1b850f075f +oid sha256:fe99104e7a90b27bbdaaa37771e9d4643536627dab2a7d2f6666883a670305b8 size 83920 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.neff index 5c576b737d9ff722a68ce0d0067e30e98e735637..cc8fb6d530093c8eb7edd37c8c29fbbab550e7b9 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b77e0e7f43a3603bfe9b+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:284a5071c265c48612d234ce96a5c2855f346de8b297018766db228865277ee9 +oid sha256:93be10e80f37aae00a2c8c9f70347b95ea51d3b353239048ddd63458ccbc5edc size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.hlo_module.pb index a05db28aa1daa64e1e6adf1788a0b8c7cdbbe8bf..5b4b82d0830227d769886d39bfd64ca091e41b7a 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:700fdb2999174103945b216119818f393e43318102778ceea42408cea535ef67 +oid sha256:8cd6afb1c4c084fe7551ad3e0c682b2aeed45f95e3c0899bef7f04786f8c3243 size 81323 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.neff index 5bd62aa52442ddca10951bfc79c87e8e11226db7..e60603c74b58cbdebb31122ad3caa9b43ceff6f6 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b8997c221d74ec4a7842+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:57afc6cfa83683d461e4e7a29bf91aa41b051b845bab370323414a6a7ec44a6d +oid sha256:e072da7eed25a3033cb44ef45bbf29f5b10aa885693280937fabae1c1ca6a04f size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff index f0ad67ca06668adfbd0292f90c3ee8f2b47f9816..cc94ec7ac9db09344656b39a7e03d957cc675acf 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:42979cd0ec9a5f3294698a306d1083ffe6c98f8a98fe89bc2760dfab9097396c +oid sha256:f300f691dae9d2002c3f7f5cec9b3e5334a014836dd10dafa43b35876ca85c22 size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo index b248385fe494ffc7cad59a16508e903029cff1d6..7dcc6cbc18addffef233bc9ccf4d5cbde1182afc 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b5ee20aa4f1f1686fd0bf72fcbb970e56e5afd7f78ff60bcfed24affa4a8fb80 +oid sha256:0602acfcc75394c8a15ae9b0ee12428b9136ebd1a6815530e85125020c756e59 size 193010 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.neff index 804e207e2418e3f4545d81d6c5531911c6bcbabe..50b0c90ec7bca6490d08d45f0beff93b58ffcf76 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a8b633e19f1762738f127621ff50d126405e0aea355b8abadbba521b3a4adcf4 +oid sha256:26c9671c2035721e908ea3693b9c18a095943a349651723af68c0a6e92607773 size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/wrapped_neff.hlo index be98b35c896f791f6941cda19904560394773a3d..4faabb479fa53acd61b2558ea524ac45d685e424 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c2d3f01e87cac25e1312+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:44e64ac581f0a7cf925adea4b412b0e40d764dcb011500119d451cd986f5d4eb +oid sha256:b1ba05d6104abad21565e0be48ff0d35ffc049e84534281932737da4119086d4 size 247153 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff index f6c9c6a98043d9e583d7703d88c6b5e9129fc399..463d33afc2a012c3a9169e9369b92ddbda8e3c89 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff index 96d2fd66b7b404052a3f52202f94fe5485d46ebc..174cb1dfccfa928743dd2418a1ac39e5efbc1401 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.neff index 2d43f71f7fbeffaa6ff9deaf124ee62df29ba049..80bc46753656cb72d5a98dd8340d135540b7ad09 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5b1ebf710d7cc5b0de84ef8e7920dcd8eb62252bec30e4f2e0da985dd31de9c7 +oid sha256:04e4e980cc409714d60aaf8a9f6f3e24e9bc475923a9465090d99f141a3df43c size 216064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/wrapped_neff.hlo index 7c4d2866082836642c5ba9e5cfcfe24ebb8cf7d6..f94069ace9d9603e92fb2dbbf8b7306d1cc16ab5 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d43edcfa396bb5f7fa37+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d42680fa0b68c035ecba291608b9ee78d9dce3a1d8932fe01a4eae9bf2d77e4f +oid sha256:5fbbefcfd9660bdfa6bdc409db463a997278a4338c66edac31c5439d0a270599 size 223770 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.neff index d67d9acd6b2a6fbe231449b40669f6c331329d37..41ff7d1fbaa35347f9c3c4585fd6cfd01f94b765 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d6c19a447da67dfa686e+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:12baa0e6a5c8ae2d90ebf56eaa45a53f8085068dc450b5613927eafcad8e1350 +oid sha256:5f387fffbd1e13cc61eabd7859d7ceb3cb50d45f3857f2d5e9dfd9ab70585694 size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.neff index 039a66e561ea3ef85fc422e11159c84552cbd1ef..debe88ce6b95c93f40e4905a20376be5704d1003 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:90011a7b74cd8cedd21beab5f0105b67a975dcd1c99a509a7b76832aa6c4c8ae +oid sha256:b5454a49e465b6d23d25c0d7b0c36e8267e48158731e0e39a1525b6bd66d9c27 size 2151424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo index 110a46367a74635e4f2ec80e2b4eb234e05c4d8a..21e8070b67996501f17cb1f992e43b17986a4cf1 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:930529517954a020d452a7d3cb9ec3fc249379cf44b05340e8a7e2993dad6a19 +oid sha256:04d7af58df8295013b31a8a8cee270b01a7b3cc4a87c04e4b1b1c7a0da0892db size 2221053 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.neff index 63d3a49485f4766ae4f97ac71cffee3dc827081c..e41316ec4fa5d16b74d32dd5d151359ba97bbb72 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7614258fc592bd21a671fc29fd833fdf6321eab9923b28bdaa281a03ea028aa0 +oid sha256:b4a798744cfff25a711747912bda678ff25e32d5a5c2fceabc3ec49b47b18ebd size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/wrapped_neff.hlo index b72fd7079202294281d082b853096297c8c1f04f..5364cde11dfe757dcae40d406fa11abcbaecf9f0 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_da644c4824015946da20+ca355898/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0652c2837255ddb07aee5fdffebf5b8ae68da37845f1e83aabe3f152b2b40db6 +oid sha256:1f04055f4e28889b2fe463623cfdda219529f4ad576a354b039c93ae806c6de5 size 258114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.hlo_module.pb index b45c639e4a7e818e4d96f69f71149d19b10389fb..3b128a2e8244e3106c385df41f72f4172a953d60 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4eb25c443d6cf2fe2e2ab55b05029569a1aa3e75608c0634a8650533b06c46b4 +oid sha256:ecfac370dd5392dae58ca3ed5d7e455fc42a1b56024ed551db8f52dc721cc25d size 46622 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.neff index 9e203f494f922b8f4690c863f764105ccdf6534f..4763c27fd7e637fb82adf9d6d6a07d6a078b1c31 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e4ae034a0e6bde8dd152+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:23194ec69f19c8f3023e75314b47e31e462b52c4e3ad5482c7c5871a4fce399b +oid sha256:d0f603a8ed8b66348e10b3604721f1fd22f5f9897bc5314be92e192c8357bfbe size 144384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.hlo_module.pb index 14baac76b252c4f5619625e0bb51aa8bcef52a52..cc420dc69a9e517a57ccea5c53c674af7d8c83a1 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d4135cdf3a474d12793ab55474180091c957ef032abef7de650b0a277cb2048f +oid sha256:3582a27059a52230d43e2988618143159fe8519c09f7de81f79bd665114529cc size 47478 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.neff index 83b0124ec96368bc29408c631698f5485dd1a727..e69bc3977b4af7c0fd4d232fa4f1edc04b847de9 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9c7a317b8ff33889716+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1b6c609b2232870f2babcf7c062f4312c306563a2d58f3f7cc7589af54486206 +oid sha256:1c2ed73481e37e3ec8244c6f3131faebf27605ba63b9f787c889b21bd2b319a9 size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.neff index 3811d7917b56c964461723a18a924339eb13ffa9..70acf7e9fdba9f34947c373d38d5124e0afd18b9 100644 Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ed6180267143dfea9183+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.neff index 4237d3675e8adc880406ba92a59b454ebffd67c7..e12d058285701a37931d25094c0f2ef2b79fdcbb 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b0257059d9e332b0a165601211a0f5a11c8471c1f55ea42fdf23e2fae04d278d +oid sha256:632eaed3a7a53e325c118ede32f7c9f437875f1f8a0d1e9c799a7730f9991ef0 size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/wrapped_neff.hlo index c74a39bc36ecc53c7de6692932a6e7762b124356..a20bccda6431c1707260475058f9ce45e63accf7 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/wrapped_neff.hlo +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f95e3cf0271f5c661734+ca355898/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5d618b554d92f95543e636879190f32bf698d8094c33e0a648cdff00e7a4e58b +oid sha256:eece31bcd2270149a2298caa2174371039c3e809becf2f2e842e7d660e1ed08f size 258114