diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/394ba8149659ea39ae01.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/394ba8149659ea39ae01.json new file mode 100644 index 0000000000000000000000000000000000000000..3d44bfd455d0487e0846e835ccce30071f3c7dde --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/394ba8149659ea39ae01.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": "2.18.121.0+9e31e41a", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3f77bb65ae5a6b9c96e0.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3f77bb65ae5a6b9c96e0.json new file mode 100644 index 0000000000000000000000000000000000000000..ddc440d9b0a2401460f8968f56dd24c3ffd1bdd9 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3f77bb65ae5a6b9c96e0.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": "2.18.121.0+9e31e41a", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4d418dd59449dde47dcb.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4d418dd59449dde47dcb.json new file mode 100644 index 0000000000000000000000000000000000000000..83fa5f665ff1ef23e4de27f8fb6a2057ce9c958b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4d418dd59449dde47dcb.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": "2.18.121.0+9e31e41a", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/7c28c8a88c5d68b7a0e5.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/7c28c8a88c5d68b7a0e5.json new file mode 100644 index 0000000000000000000000000000000000000000..deffee74642e485166beeb649c672cb5a91c3fdf --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/7c28c8a88c5d68b7a0e5.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/d2cee631571498108c74.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/d2cee631571498108c74.json new file mode 100644 index 0000000000000000000000000000000000000000..f928eb1e68d658968fc481a9e4662930f680e828 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/d2cee631571498108c74.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/e64ce62517cdbdc71dae.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/e64ce62517cdbdc71dae.json new file mode 100644 index 0000000000000000000000000000000000000000..621dcc4d389b66167aeb4d1bdfa32998b535108c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/e64ce62517cdbdc71dae.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/e0240f41c55198f5b4a2.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/e0240f41c55198f5b4a2.json new file mode 100644 index 0000000000000000000000000000000000000000..86e1b54581891e79c4ba693b4b81bf14ec058cd0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/llama/unsloth/Llama-3.2-1B-Instruct/e0240f41c55198f5b4a2.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/cc6e87ff362c7755dfc3.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/cc6e87ff362c7755dfc3.json new file mode 100644 index 0000000000000000000000000000000000000000..1981eddfcb6873a1ea3fa8edce28723a9e5b4f22 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/cc6e87ff362c7755dfc3.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/ea665141c31d4cbbb111.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/ea665141c31d4cbbb111.json new file mode 100644 index 0000000000000000000000000000000000000000..566041f551641218695ee4ac1f86f60cc1600df5 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/ea665141c31d4cbbb111.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/eea019da9ffc7619dda7.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/eea019da9ffc7619dda7.json new file mode 100644 index 0000000000000000000000000000000000000000..be7f2f9ce8ae5ccd95cb835be37080142649bf26 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/mixtral/dacorvo/Mixtral-tiny/eea019da9ffc7619dda7.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/46c220062dd86ae6025f.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/46c220062dd86ae6025f.json new file mode 100644 index 0000000000000000000000000000000000000000..cff149e8e19194ed1910d7208d44c078e8583887 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/46c220062dd86ae6025f.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": "2.18.121.0+9e31e41a", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/773fae5d2cf3af166253.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/773fae5d2cf3af166253.json new file mode 100644 index 0000000000000000000000000000000000000000..342802f15580f464eeafc9366dbde70129576eb6 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/773fae5d2cf3af166253.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": "2.18.121.0+9e31e41a", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/ec89efa8bb14d3c6915a.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/ec89efa8bb14d3c6915a.json new file mode 100644 index 0000000000000000000000000000000000000000..96970806c6f7c27df4f364a347be91be565be33d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/phi3/yujiepan/phi-4-tiny-random/ec89efa8bb14d3c6915a.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": "2.18.121.0+9e31e41a", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/1c7306d39a56777c651d.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/1c7306d39a56777c651d.json new file mode 100644 index 0000000000000000000000000000000000000000..46cf033563bd652cf4b813b02efdcce97108a9d0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/1c7306d39a56777c651d.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": "2.18.121.0+9e31e41a", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/5fefeb68e7e50cd1787e.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/5fefeb68e7e50cd1787e.json new file mode 100644 index 0000000000000000000000000000000000000000..60500a642d7ea5f944a7cafe815f369d01221beb --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/5fefeb68e7e50cd1787e.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": "2.18.121.0+9e31e41a", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/8fdb7edba36a465a665f.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/8fdb7edba36a465a665f.json new file mode 100644 index 0000000000000000000000000000000000000000..3dc5182f9285c1c744add9cae94020306f9dad1d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/8fdb7edba36a465a665f.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": "2.18.121.0+9e31e41a", + "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-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.hlo_module.pb index 7359325a0783ff9ad9034ae4e5dd8e62714d2b3d..35ef9aca362ca665e187a56ece1191e86bb953fc 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0803cb5e5e23b32611e1d7a9f6868f512ce57b77d3a0a29c8f986b5cce743321 +oid sha256:aeb35be7b4c769876dd61e1a759d13da8a6c34881ccd1757aaa64f7039b95ea8 size 46622 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.neff index 987d7ee6224ba9979b04f56f800dac38e4181d8d..fa7a981e8c2250fad70de3c1819c625c696e3d8f 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5230dfb96ab51bf16cb02ac63f3e8ac41c847cb011db0f82f5001847f758f0e6 +oid sha256:24adadd3501a511aa2f9f1dbbd493488f53843ad2daa88d6920bcd471b86b608 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff index b1018ef1f58be407d3c7a6e089c2d12cf7433613..1ff2b334eef31c7cb2fa49c6db86f52be0ad5c97 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4b5cd54ec5279c4dde9e6475b7cfaeda2aab62e3e2a92fc242c1a56d05049874 +oid sha256:5783bd343ae3fdcb8313d9dc3b23d3a9356c6f8dc24505e32bac20b2b7adba6a size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/wrapped_neff.hlo index 30f7a3968098ae5ab53415125524bce923d92694..ebee7b2a73a6a9a630570a01c9c86ee6a5efc29d 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bc1dd826502c3a5e1b83a630e5959c0f82c6ac46c9977cc351feebcc5a0fe5c1 +oid sha256:53b455edb9ad0d00f2e1dbe356f9574eeb2ab17f99756c60771074e81f234af3 size 247153 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff index 0b17cd8b1850886dd2143f1d37c70bf01c814d61..23a78b8cf3c95f309c356fbe4cd166db21bb8abb 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:60e93f84fcd9ed08889336789a60b971c3c21a507ccc034decf8161453cd443a +oid sha256:05c5c5bc8f5599a78c6434bc2b088dcd7c9dd1df1b0636bcac6f7ffbc702d1f6 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo index fbd0c7e303478f30c5082d31a770638d1fe91b9f..d38b80c383373eb354023a7564b9a90d5186050d 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:885b920ee07701ecbd3ad5016e0df8b9fda3c38ce8ee8418f9978ccc29609f40 +oid sha256:c509b3f043adb90c90d629be73780694aff7b0f465526f919c5de301bceb14d4 size 152045 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.neff index 15581b21867a193bc088421553f89f703d01f860..dc4c3404de00c7afcd81df6a774838480ca34996 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.hlo_module.pb index d480daeaf8214dab9142e56d41f296ff2d4e4dcb..8ea202897a899eea0c527a2ddb36c10a079858e7 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:527ff38e542de60af8633e078ec3c5c57fbadbe30d74ee1aac584834b1615288 +oid sha256:dc5820a8b0f2c5de27eeb3167bbd6c7ad99cbc6e4250b487d89a102ef1a236af size 53803 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.neff index 78496818354281ef44d85c56c692a18fd9d98168..ab88a732040465cce6fafe16c79648300de7bef1 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d6869ac00c3e40d1cf9945744471e75dd98b9e6b9571289427d0902e068456fc +oid sha256:40c87ee01d8ab4c3c744687040b92c2674201d2fedc2f318e1d91a5c8213e81a size 164864 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff index 6a964eedb9054da949df79ba9b697b3ccabe15e5..27003a0f969a0d12fef0cc0c56ebf0ca700fae11 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ad2f90d77e4a5f3f591bd8b664f2daa39b197f27e7c946650e8776e7a9a5d0fc +oid sha256:c61151ca6c4e98324d2dd643e5ebd2dc7136090fc82c49ecd0265025d98203c9 size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb index 2f4073e68c06d04faec63596277fcb102043a1b5..a16af079cecd4b5b9160b0cc291f7046870e77ab 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b25c984cce04ac74df62cd1dc284c28470313957cf8e49fea854099b9378ffcf +oid sha256:77bd2663c3810b6b6d6e3248f235ad11eaaea050da0bf32e10c8f17c3299efe2 size 448722 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff index ebb60816a5cefca38a717b70f287885efefb60f4..b1b22a0e2079e4b88f6d8e3a98f458619afafab5 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fafb376e0631f5d62079fe5c78eb54c9982815c07a92e4dd51e53e801f78048d +oid sha256:52a19cb8631463a2a4f2eb1f3e41aba5fdb2b297355d92f3b99e6bcf0c79691e size 32257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff index f176c2ca8ad31d5e1e57cd552284527b16897e09..1ac128d3d414af69cd51d62ea2489c25e9a87109 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:08bd07117299b6a109bbdcc2de25721ecca088a812d7ccf82129137817b69a44 +oid sha256:7f5e58e36a41c0b089557aa450c98b3d4a45c290dbb22a12e7d4335fef917f2d size 164864 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo index 013c8d352f7ef365445fcc4ffbada708ed8e5ea9..cc3aabfd777fe5ba4d222d5826229a671899c7cd 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f2b61c4890b4861116cc151d02681a4e10deda4aaf1728a6a24853b73747001f +oid sha256:479b0c170ca81520f7c4fcd3aea24c3a0c85995f90b64f42619db6d90ff23302 size 172461 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff index b8c17eab99386889e33629e9716c37f374ec4fc2..7950310d0a51780840817f9c906e8ece6aac5557 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.hlo_module.pb index a69f1c26eee3c0487ceecd3b0bfea313cd8db96f..4f9dfbe1e0be4b202c596eb4f6edde2916b33cea 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7a84e2c4df78dd443728551a6323c507c957175fc24244fad6ae2771ef852433 +oid sha256:dad13102e9bd32be98f125c4efd1ec18611c949b07e82e8e2b4a89fbbe18cc57 size 83856 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.neff index 277cb370a8d96d6dc2226cffa217e5c4b7d40321..ba04794c6da77f251ed20d8cc8263e8b2063be79 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9ba992580776ec3af728322a3b16baf4a7fc3238ff50b75431e123b378e170a0 +oid sha256:5e8664f1d6106174289c8218f47a1fde759745930f0726cf1324564b5f0336b3 size 175104 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff index d672d6bbe05e2738399a31c6d821241b4954a185..b155eb30125f7899460cf98c4d0f1529a7737778 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e9c035847659ef48195627fa9b0edd5de00a79c72a7f9d5f84fa4ed48dd96e8a +oid sha256:fab9dac62fde66d29ca013fd3635c66d7776f2357fcabf475227c0ce23479fa7 size 216064 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/wrapped_neff.hlo index 90f45c9cc3fbb02effa1c8982c4f0ae1799e1b79..ec712516c91b12a81eda0255d214198c166d45b5 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:508c3810dcee0650a55c552d9a1d20bc4b687866e5363fea46a5eb1eed230ee7 +oid sha256:0d0da1d38f365fd2583898c15a59ddee1b122e9fecaab4943efdf20aae8bd1fa size 223770 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.hlo_module.pb index 199b4ffd2485b205312dc8d865182fdc52460b48..0c725faed444ecfc5a8a57c376abb8953a9533dc 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e47f49ac892e885be490920dad61b26edcec9067ceecd3a32a0a409e6428becf +oid sha256:40969194a5f66b5cc929ec86015e06383d410f8c7236c19178b919c26c782b86 size 87721 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.neff index 13213f0c2c7c55c7beea7310170b37fe4361fcc1..052ff8d5afe380fcab96507be0a2bccd234660e2 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2d54b77c463aabfc605a0f320223ce7eb30f740b6e5a316eedaa73118a4430ee +oid sha256:7cd0f7a4fac7ae2fef50d6502a1371140fbd8156b13230d52ff5e9d72c2ff5ac size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff index c6ebd6ea9ef15cdd675d15bddb79faf6ced08a51..5624e1b8d0a5eac6f5b645d348b157e78189c4e6 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d8b7088016b28e05bc300a1c8ef5dafdcf09c8ace02575054444ebaa57baf00e +oid sha256:35653481e484c459b14a7ccb13532dd346e12ee110482b9052fd32f77f900e8e size 1158144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.neff index 8c3e72427faf20b1aba19087ed2603ecafc50c8c..efecd80a03adb5e2c6a88e5a346359bdbaa359d3 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.hlo_module.pb index b57745fc2d05b1e03261573c72bc2080b5fd9253..6b5be5e4eb172c160879140b47de4e34654e832d 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9db8a869bcc82627d232ef994835bbbfcaee6907910ffa4b8474e57b46c44aef +oid sha256:2f5fc5821a18a923d93067a2dab3deb8a1ea77b78e5d3a2be6096277f02257ab size 80405 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.neff index c7e11bc358d6dc36f09116d5522abc6a67378aa0..a1636ea849694cb9141ea664cda006ffde162eb3 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:838abe20817ce441de934d90c5006bcbcf7d7d57e68feb15129318c8051c2bd3 +oid sha256:c959eb0a7e13ba0edc9e91dd947d82d1e12766b067f60d0de7accff36c3d365d size 205824 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.neff index 9bff488e1b5e7955022730d26164acea287084dc..465b4f42c07c80f1eba32b94277845ddaf1fa0c4 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5c7db1459ef8bd7be49a3f56b30f1daddb6a4488d7940df1b2fef1c69dcd0aa6 +oid sha256:4974299d8936bd1519b4df3ca6b7e88e9da692519955e41e3537d33fb61fbaeb size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/wrapped_neff.hlo index 056417c5ac1fba772856ae706548a0ca936866b8..4942283c10bc9e49d03010c4b6d1c55187a6b01a 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:20493d9e2fde14fe06cfcee45e4a1f5f8c780d6e47c7df3996dc3ca1f6502849 +oid sha256:71c4e7236b91d6e521abbd93b345612cea0e2ae824d35f368ef40d711a6771a4 size 268322 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.neff index 808d8e58f78e93e3b951f24df9f3e5793b47c062..15488f3b740ce2985dabab385e845bb4d0697358 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0746e9e3250dcf63f7996beed4c4ae2b68b9f338223f1e5a183772052e3318db +oid sha256:4ae7afef0b01868c6cddc354d06639bc0f646abcb15ac11076e0ffdc9132f6e0 size 185344 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo index 018e51fc360c34c67b8dbb51bcb81f242ed0a95d..6466c0f5e83b827fdbb6c04c89abe144de6c4808 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1de43537186c063d0753bca387178e708ea05ba20a821eb97f258f432886e849 +oid sha256:f75279e91322df84c7f2c47dedeed1efa3f0bb1a6a865f0e26a45e76a1bce1c4 size 195507 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.neff index 201dd18af4cad2e17fceb960a1299f1a1665eb6c..e1c428e27d9d6679ad4b0509dcd0fec955cbb670 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:71149026777d06d0cc0885f4527aab8b53141395290e5f9ed57611de45157720 +oid sha256:05808bab6fd6a5b1c3324df06931d8e1e92fe076a37cd170b683b8e094f4c9b2 size 185344 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/wrapped_neff.hlo index afe812a53d429d467f337cec936b2a01757de301..fd22766522ffba2037e9605d37f74e5368330044 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2900d852844bc8462d53b0987336ecbb2619e53f461ab8eb4d54a0ecfc4ec0d9 +oid sha256:c2fc774aeb66814bd527397e18b098b034f48bfc5354aea68fae0ca100664b14 size 193114 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.neff index 8104a4b674a5d71eaf6edea1576f7e4f260d602f..df9922ff1427b6159c1b17da368cdc94f7725507 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.hlo_module.pb index 96fdd50183be4741179a4272e8a282757a1527ef..29654d67286fd1cea1336649e3bf84196f8db754 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fb65cf7fc2975320dabce897b5f50369c9bdb4062f74a252f32ca0418771b03f +oid sha256:e7d0abc6789528ae294d14222f1a8453446c6a4bf4fd827cdcf9ceb646cc94be size 82456 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.neff index 5f295f9538b136b25cf1a49a06b87d1c679e711d..f0106fc0e697e96852460d411f8a3dc358d20fc9 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bd168a7d4d1fe94001bd9677413bc3309d5e07b232f1c1239b9907de94cb6f98 +oid sha256:df60f36c3a3deb0a83084f779d69657336d0a6e6e5ca6d55961e365d9c296da2 size 420864 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff index acd05c4c423a5fc8705984904f4b5e791eb1f912..8bc6c94712e86f3f124eb53f480fed2d554b9250 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d6855df2ac066cb4d6a0f3b5dc367c0c68a20fdba555473ad35c98325e6c7086 +oid sha256:9887bea76890c89a51ef04bab244fdc78ba26e0a5bcc36bee93c9ec146ca80eb size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/wrapped_neff.hlo index f19b5602d37ca9ff6b5e90a6bd3d72b817cf4f2f..87959b3caa825ad50bc34da82c58ca99d7f4eaf1 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:88391ded313760df6a080da418fe8f7755a5ad14197302b457aff09a4562e4b9 +oid sha256:1008adbf3f5c4472c9fb64902322cb8f4263a85e6d21b4f722065388cc5ea069 size 247153 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.neff index 45f0914398a88424578d7d94701bd1c6166f7c40..153d4858a2def58d06f0910910b3dc5569525a6f 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9526127ece1c2fe911e0f7f40e043c8e4bf016adda4812373ff0a01ba0dc1927 +oid sha256:efc73132b56ac2df12172c6556e9407d72a721c96c89911c04e0920a0130561a size 318464 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/wrapped_neff.hlo index d8be7a670d157ba8bf9d8ee01cf73998e3602506..87ef01e043afa7f943121d8f53776317e51f8066 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:939ca9bb793aa9de3af13858f266ad4ce857c7f8ec589b4e403770a266726bed +oid sha256:a34e1924c7c43ebe695beaa608416415b0e144eb0fd5fe12a0ab4ed68761ed61 size 329762 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.hlo_module.pb index 983736ce70f0efd578e4e35e21d78f6df84226e0..4c1e25081d49cc08332dc3804f24e6d397bfda55 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8c422fa53242d548d1ed934ef136f4306c2fe868be8fa250e7fd1cb33f37528b +oid sha256:9560729d84b81b55f6242b97a7f14cbb79e113cac28bd8a05c312b3fc5bb6af5 size 81259 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.neff index d26269d47ec2370d93f1772153e1e350f8e6d787..e210c3e461d69a43de9c649a0d6a718b68bccb4c 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:afc9f8d3517880c1e3910a7aabc7c4217669e3dc94db594196469c9dcdeb2f9c +oid sha256:496df920e2929a894d1915aaa87b5776266ceb186ee45f61ca294a39e8decc39 size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.hlo_module.pb index 2457ab4c3579f2e12083b070f659d3dcda20c79e..ee01987d8fea78c9e3321f123b308e4f6be3ca2a 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:570bfebad16e55f606a846e758130d43a744fd0a3e8f6fa0383c0386a7583e00 +oid sha256:b25002db7231bae8409e8575e651d764c92a97fd184226d6b68c74150529c7a9 size 47478 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.neff index b0f2fb71a56cf1e06521132f71c4df4bb53d8caa..3fca6576ad4c52053bbad96e510acd02709cc208 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4ce1df856e2b1885249aa88be122283e80f946352a72cfdb595d52bb0cf358ba +oid sha256:0f0fb65d97090aebe5be439ba36788426a56025b2eb19f84a3b6ec7ed3efeed8 size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff index d97c220dc7da95d4b01469fe302f1734b3c3b48f..556a5366e7af54ce4daf30b1d92abbd8b05e22cf 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.hlo_module.pb index ca4bf49cd2143b234b9c5e61c442e674f3bcaa82..d2775f1d4b8d8d94bed0b33f284658df021e1c66 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d07be97fa86bffd0b9d5b2cd5c17d02b4523838d7a6e300d15ea296c528a399a +oid sha256:ac33740e4be62dec7fcdfd5490be587d4696a51841b6e5d04322a760dcea6569 size 87721 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.neff index 62b6fa21c9db8c884029f3af3e333f0543b76407..f6caa80a97a01b5e688be1606af0e52f82fd4b8b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8d5a388f6f5f9faa0ac06b07f57fa96672ac68b4b7f88e389fffa06505e3de9f +oid sha256:aec8d056ae18a72ade23da309945d6fb62f756453b3668d698af5e61760e395f size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.hlo_module.pb index 5205dfeea18bf1cf496181949883f69c42096f8d..007190013d837a3a4595b929cf9bf425dd4f362b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e14d263b8dd1b33d02b7774c9f93e3feaaf593c3d8faee15cc31218d64254487 +oid sha256:4bdc27528e59d0b6d5c517520e47ad7429ffbe2482177f6c96c12ea4dcc9d534 size 81609 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.neff index a98bb2d7db8804c48177d253c6219803142ac8af..30a8e943f16e5425991b18b6fe7f7bbde1e013dd 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d188a74cf47606fb51e0a0db14230a7e15e4319fcf899c86b85a9ec05bc6a843 +oid sha256:b4eb47f8044331932614ab0ea1daad029f3e2cf496137112015392b2d39b294e size 359424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff index c709404cd4b1e6c6b8a68dc8b48cd94870b43868..f384411ddce1d50dfb8df1dce0c11d01122c1f25 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.hlo_module.pb index 8bbaf1482e339bb678062269adef7adbfb3a7486..5757050f47f794ba268a3494181b109bd1f4396b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ad9c9788c07b0106ea9b8b5510e9e1f32e73170c6b3d226518c963f73561f3ef +oid sha256:f5ac166a57fc89449e139287e376144273d21be8e224cbe9a0b67b27a1dd80ab size 81607 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.neff index 46c36ad26dcea2d1d453135bfea9bca84562ccc5..0ba87e93a35682a0c8038de40bd2eb1e9253a785 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4102af754aa30becd34f0428c25cb18aee8cbe9a64b4e419fc555dddedd15946 +oid sha256:4eb94ce2348206ad1fcfd80db057a1718eec26d98a1dc5a29a9ce1cad80da81b size 359424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff index 032023f077983bb869b0f7eb5d6a8114293c1514..9f615a4bc3562d93a6ae9c89a591f9fb524c981b 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:434cf82dae352fc7f13ff37a31ea63e6b103871c072ea3776455dd867ff3c062 +oid sha256:4a2e399bc141f4e654a255807c16e488f60eaf6f9e43086d575c1bfe1a6b529d size 216064 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/wrapped_neff.hlo index 25fccc225f1a8bf15a22e62e787a8bfe274053fc..53e6c5cad808e3574bec5ac579a7b65b062ec8e5 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2de72f53fe6a8b97a6fa2db6a0041cf99fea43556787b65b69b9e8d82b861bd8 +oid sha256:e416e7e2627c9d1d994ac66c657eac63e1b50b90983ff22dab7f996a9697f11a size 223770 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.hlo_module.pb index b990f6f41b9ffe22eba92a7d7ffa5e6d75cbad8f..80f07a4efa04bcaa87293697e1f7726717533e50 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:56600f1172894a3448f3ccdf32787794fefdf811f5733ade4489fa4a2db37800 +oid sha256:0332bbee1b66a83f5bbf7930ddf02d722b791330649e3b6321719f8401e39b27 size 83856 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.neff index a9f4de062d84e7b0603a921353e5089727e7ef7f..6bbbf975fd61ffd7a4e38873b6fcc9b9e2370c5c 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6d5190ca06721070d96bf93dd2fbd4df4675ebaea3a183edd157be63390ab807 +oid sha256:621dfb88fc8c41894ab028ec7c5fe8b7b6d6bcca3a0c30abd6b18cceb051c788 size 175104 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.hlo_module.pb index 6b715038ef72dea23f7c5415a5754b27680c349b..ab0e2ad82a7fbcd1583eecd8be0e15ee6a67742c 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b76b2f95890dcac140043403bb20c0bf74aba7c28c4ea6c6c15cfc8f3264f926 +oid sha256:cd71d207c8490df241e7afa155f7595bdee001730966d0665cb9b3bafea469e3 size 50076 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.neff index 492450bfcf917dc2663e74354210b25ca10b850a..05486f5cd9fdf2edbd2cfea47bd3b481c0bcf4b2 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1a6e0f7f0e41859d9bc51d2a44341d1ed158aaf09fb56414c948579ea33897f4 +oid sha256:d3ecd4d35df7fe22cc1528caae425ae84a166a0ca471ba9c71a0c736099f908b size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.neff index a5c46157b74036f50f76f2308076c73457cf791d..66811f549d8f4c7372172bdda66536dcc9b8f109 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8943a443de81c9a48f62d60326f7f361df9d7d02881d310f39b559a24ac67741 +oid sha256:685d8a23615123f28af5cf4e235eceea219fa4489310aea81aa8c25882ec0b5a size 185344 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/wrapped_neff.hlo index 126fcc784af363dddef9b748e56f78ae5c31e01b..edd66a9585d0faa278509e75f0dcfe944b288ff6 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9cd8008a48010fa2ebb5562edfc300e6ae9d15a4da602df96542f9d34df91aa6 +oid sha256:58165e7d27d83d1f9e3b229ff93cc38cf59e47c612d5add5014e425f0ea90f75 size 193114 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff index 765da7a5a783d44d4dc68e543d3b9939a0b03b8b..e85e192123d6588c50c1fec0fbd63f27d8ac61fa 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.neff index fe636e40cb8919c82a05ab1509fb3d6204a23f2e..38fdc6d10ae66f50c6ac711a028578b39c493642 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff index b8f24d640364c3077dd395fd131cd32396928028..78c5939edd7bad6d431920fcea88e24fd7aa0575 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:09f15923d617ea3b6d706282e407e6c7021800985700d2ed3ef3e15674858df7 +oid sha256:f7e7f93eaba703cc653a230fa4836f23939e6c7a44522fce02f632bb97225b29 size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo index c3146cafe72505e8fbb492e2d19e15be582c5106..e882b74bcbd577202d52dfcc86551b41e8d6baeb 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:576aa1375944182960b25392e1220e9c5b48e7f77a4dfd668fb4e2d88f0968d4 +oid sha256:9a461160defe675b2a9f96ed14ad654b4ddec475dfe31d53f512c15862185ffe size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.neff index cbb9255d26275b2a8c00b45cf0b28cac9fd3d0b3..3811698649264b1e183d44e6c0409fb59b76e958 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:33d9e47ee8c786bdf78acab98008da7248525740b8d2e6bde0f79cac2f95af96 +oid sha256:0f1c6d2a0ecf585900f432a4c33e3340eaa6deefb8b4bda3748374c5c8811539 size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/wrapped_neff.hlo index 6ab028e506d736152538e415663706df15ba3177..7f31b855eda4bbc9380d3fd55fb671b6f8c1f121 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6a14e5f2388f3ace5ff619614bd3dd2109944b3251476a0131a5a93cf7ab8ec0 +oid sha256:ef8a4e2a2d9a4a34e428477898791be74cc52f335b21b67da8abe2b99564fd2d size 268322 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff index fc65e7c35cfde71adc86794f2000527685c849b1..e1c8378f14e1647cc49e464dae02c3494fe9c9cf 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7cb3edeb207989258778ed70657636db6bbc288bc7ad9ae6d805328b27b64679 +oid sha256:d8517c41322f7526fe6b17837bc1449f34dd0755bf2d552db658710860e77c5c size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff index 7212786f56a569a0d6ea486b65c1085d2389a255..889590cceac3dc2dc0015e65daef671e45cf3191 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:61518720f5c1a56264df8a0a25e057d2cd0e5babe0e9df301343aa3395553c99 +oid sha256:b233a991e3467912b9d24667dc845dabd567d05e9006cdbc7677452600825fc0 size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo index 01b57aa31cfb81dc28ae5c68013cabef3f7c2482..8ce4e120a9e6435c7b50265a7ead2a86b88124c8 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c61433f19c2c34b5b69640ce4fb66dd3e27b67648ab281ae8b82fa7f936f1dea +oid sha256:dcbba938bdd7bb35da625f86935134407ab9391c58f554766bad9eda4729634d size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff index 7893b76dc5bf5b93abe2050e7ce0634eda60ceac..157d3bfea61335020be49102d8f3721a1bfd2a26 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ffd5770b8b22036f0c2e824d9275a5fd7e7cc4e891fd30d8cbd0d66d3c527944 +oid sha256:dde397bea6c2e41f1d4e4fea25dc752645e9c08d1f088d360a56237022608283 size 175104 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo index 0fa49fc13f899059fa8ed513b8d31ef782746808..baf61728053520200ff5ecdf9ba8141d70445308 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8c4c53821d30e4390bc04b9d4e0f98107209d051510fa7c921a9b807d1252973 +oid sha256:87da579afe3ca22a45dbc820ec93cf3bd0ccb34ccd833c1730635150c0ce0796 size 182770 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff index e1897c0800c20472800267f4afdf5c7e1db50d44..37d2ce60081136bfd33029693e1e032196fead13 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff index 4eb3cf53217c7acb7542603ea635db879ab3800d..12573a0ed86658bcc880843906a9cae0bd674afa 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff index 8f06af558ca98376c314dd06c11d94b11816b6d7..8a0bfde2d710ba6cb9e2d58875c11a7236118b01 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ff51b1e8f0089284c70d5ce0b95f0298dcfcea8dd1761176e4db4ff482f2ac26 +oid sha256:d5438245a04489d570d8d10aa0c9cb7fa89456e691695b2bc0c1e3d58cc989b6 size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff index c3e477c36ff6cba08861d1302e38ff91316b5137..a105f7a83082631eee02faab4d46e0ea1744fa3b 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.neff index 605c70da69142f1ee75b893aa539c67fe25e780b..d39aa39ac5818b6f4af98dc749c783b179d75d34 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dd673a3965624937245ff5a02c3d3c5b9b119080bac8fdf5f1843f29fa180baa +oid sha256:0d3c0eb178213d2cd373b07ccc737f17ea31e523fe16b8623eae1ae882dc7541 size 2151424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo index a43a34cdf93af84a74b1c39a219058b9e38375d6..22816286714eae412f8cfeadd0389053ed2513aa 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:73cb755bb80f3b339f8db03a1d6cd1e254d4c04863c9221950e93e3bece6d458 +oid sha256:769b8533ca559aa0b9ba0f5baa438b3799e9e9b4656773eae6ef44b483133c63 size 2221053 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.neff index 5a604ae92498e8dc631c831f78f52478b20cc60e..cd1b871ade267104eca61ebd2f21ed4298d25e5b 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.hlo_module.pb index 48aea0484012f1ee57870e47d4083c5621df850d..e1911459a68bdd22bdf1a1e3fd54b774b99868e4 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:41b75ebf90847829cfc31c659cfac863e299f261af49baa91f6d38d37e0b46a5 +oid sha256:f12cbb66e730dd4bc5b4b80513fbe910e6354647a438b1a14455181fc6311799 size 81259 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.neff index 1b81195663b62a889c05aeee3a220c8382de6109..e53769f349a9cfebe8b3e502d9a3071de3e9f7c9 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:835d001e67d90be9e65a5c8c653a2e799f0bc32d71a8f6b044fda23dfc194959 +oid sha256:fc69999f85adad9420db78fa94554c0188212129d7f1211be41df660c7ac0415 size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.hlo_module.pb index 932be66f5cb459fc34cf28df5d15aedaf1ee372e..b8192c62c4f5609623048b39d10ed87674500f2e 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:eaec5af4b4cf4fd74b2e708127f3189f9e03fc023690c0af800c919028845578 +oid sha256:6387f8bdeb0d69ef89697c49f79967def4d8aba543012b786794d0b04b1c1e21 size 80405 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.neff index 4e325ede650ea180e681cdb50db5624251a8c2fe..8b2f1457f0d63f34a3ecd3595a99579220a888a3 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:af0be1adc07ff75f1a32a1eda981e91ddd0305a961500bb331961273ef982ced +oid sha256:3431fc80dd8c140264a5a0449405fd81d4923952b4be1b54e2965466cc03a1ee size 205824