| { | |
| "builder_config": { | |
| "gather_all_token_logits": false, | |
| "hidden_act": "swiglu", | |
| "hidden_size": 4096, | |
| "int8": false, | |
| "lora_target_modules": [], | |
| "max_batch_size": 8, | |
| "max_beam_width": 1, | |
| "max_input_len": 2048, | |
| "max_num_tokens": null, | |
| "max_output_len": 512, | |
| "max_position_embeddings": 32768, | |
| "max_prompt_embedding_table_size": 0, | |
| "name": "llama", | |
| "num_heads": 32, | |
| "num_kv_heads": 8, | |
| "num_layers": 32, | |
| "parallel_build": true, | |
| "pipeline_parallel": 1, | |
| "precision": "float16", | |
| "quant_mode": 0, | |
| "tensor_parallel": 2, | |
| "use_refit": false, | |
| "vocab_size": 32000 | |
| }, | |
| "plugin_config": { | |
| "attention_qk_half_accumulation": false, | |
| "bert_attention_plugin": false, | |
| "context_fmha_type": 1, | |
| "gemm_plugin": "float16", | |
| "gpt_attention_plugin": "float16", | |
| "identity_plugin": false, | |
| "layernorm_plugin": false, | |
| "layernorm_quantization_plugin": false, | |
| "lookup_plugin": false, | |
| "lora_plugin": false, | |
| "multi_block_mode": false, | |
| "nccl_plugin": "float16", | |
| "paged_kv_cache": true, | |
| "quantize_per_token_plugin": false, | |
| "quantize_tensor_plugin": false, | |
| "remove_input_padding": true, | |
| "rmsnorm_plugin": false, | |
| "rmsnorm_quantization_plugin": false, | |
| "smooth_quant_gemm_plugin": false, | |
| "tokens_per_block": 128, | |
| "use_context_fmha_for_generation": false, | |
| "use_custom_all_reduce": false, | |
| "use_paged_context_fmha": false, | |
| "weight_only_groupwise_quant_matmul_plugin": false, | |
| "weight_only_quant_matmul_plugin": false | |
| } | |
| } | |