| { | |
| "version": "0.9.0.dev2024031200", | |
| "pretrained_config": { | |
| "architecture": "LlamaForCausalLM", | |
| "dtype": "float16", | |
| "logits_dtype": "float32", | |
| "vocab_size": 32000, | |
| "max_position_embeddings": 4096, | |
| "hidden_size": 4096, | |
| "num_hidden_layers": 32, | |
| "num_attention_heads": 32, | |
| "num_key_value_heads": 32, | |
| "head_size": 128, | |
| "hidden_act": "silu", | |
| "intermediate_size": 11008, | |
| "norm_epsilon": 1e-05, | |
| "position_embedding_type": "rope_gpt_neox", | |
| "use_prompt_tuning": false, | |
| "use_parallel_embedding": false, | |
| "embedding_sharding_dim": 0, | |
| "share_embedding_table": false, | |
| "mapping": { | |
| "world_size": 1, | |
| "tp_size": 1, | |
| "pp_size": 1 | |
| }, | |
| "quantization": { | |
| "quant_algo": null, | |
| "kv_cache_quant_algo": null, | |
| "group_size": 128, | |
| "has_zero_point": false, | |
| "pre_quant_scale": false, | |
| "exclude_modules": [ | |
| "lm_head" | |
| ] | |
| }, | |
| "kv_dtype": "float16", | |
| "max_lora_rank": 64, | |
| "rotary_scaling": null, | |
| "moe_normalization_mode": null, | |
| "rotary_base": 10000.0, | |
| "moe_num_experts": 0, | |
| "moe_top_k": 0, | |
| "moe_tp_mode": 2, | |
| "attn_bias": false, | |
| "disable_weight_only_quant_plugin": false, | |
| "mlp_bias": false | |
| }, | |
| "build_config": { | |
| "max_input_len": 1024, | |
| "max_output_len": 1024, | |
| "max_batch_size": 16, | |
| "max_beam_width": 1, | |
| "max_num_tokens": 16384, | |
| "max_prompt_embedding_table_size": 0, | |
| "gather_context_logits": false, | |
| "gather_generation_logits": false, | |
| "strongly_typed": false, | |
| "builder_opt": null, | |
| "profiling_verbosity": "layer_names_only", | |
| "enable_debug_output": false, | |
| "max_draft_len": 0, | |
| "use_refit": false, | |
| "auto_parallel_config": { | |
| "world_size": 1, | |
| "gpus_per_node": 8, | |
| "cluster_key": "L40", | |
| "cluster_info": null, | |
| "sharding_cost_model": "alpha_beta", | |
| "comm_cost_model": "alpha_beta", | |
| "enable_pipeline_parallelism": false, | |
| "enable_shard_unbalanced_shape": false, | |
| "enable_shard_dynamic_shape": false, | |
| "enable_reduce_scatter": true, | |
| "builder_flags": null, | |
| "debug_mode": false, | |
| "infer_shape": true, | |
| "validation_mode": false, | |
| "same_buffer_io": { | |
| "past_key_value_(\\d+)": "present_key_value_\\1" | |
| }, | |
| "same_spec_io": {}, | |
| "sharded_io_allowlist": [ | |
| "past_key_value_\\d+", | |
| "present_key_value_\\d*" | |
| ], | |
| "fast_reduce": true, | |
| "fill_weights": false, | |
| "parallel_config_cache": null, | |
| "profile_cache": null, | |
| "dump_path": null, | |
| "debug_outputs": [] | |
| }, | |
| "plugin_config": { | |
| "bert_attention_plugin": "float16", | |
| "gpt_attention_plugin": "float16", | |
| "gemm_plugin": "float16", | |
| "smooth_quant_gemm_plugin": null, | |
| "identity_plugin": null, | |
| "layernorm_quantization_plugin": null, | |
| "rmsnorm_quantization_plugin": null, | |
| "nccl_plugin": null, | |
| "lookup_plugin": null, | |
| "lora_plugin": null, | |
| "weight_only_groupwise_quant_matmul_plugin": null, | |
| "weight_only_quant_matmul_plugin": null, | |
| "quantize_per_token_plugin": false, | |
| "quantize_tensor_plugin": false, | |
| "moe_plugin": "float16", | |
| "context_fmha": true, | |
| "context_fmha_fp32_acc": false, | |
| "paged_kv_cache": true, | |
| "remove_input_padding": true, | |
| "use_custom_all_reduce": true, | |
| "multi_block_mode": false, | |
| "enable_xqa": true, | |
| "attention_qk_half_accumulation": false, | |
| "tokens_per_block": 128, | |
| "use_paged_context_fmha": false, | |
| "use_context_fmha_for_generation": false, | |
| "dense_context_fmha": false, | |
| "pos_shift": false | |
| } | |
| } | |
| } |