| { | |
| "builder_config": { | |
| "fp8": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "int8": false, | |
| "max_batch_size": 8, | |
| "max_input_len": 2048, | |
| "max_output_len": 512, | |
| "max_position_embeddings": 2048, | |
| "name": "llama", | |
| "num_heads": 32, | |
| "num_kv_heads": 32, | |
| "num_layers": 32, | |
| "paged_kv_cache": false, | |
| "parallel_build": false, | |
| "precision": "float16", | |
| "tensor_parallel": 1, | |
| "tokens_per_block": 64, | |
| "use_refit": false, | |
| "vocab_size": 32000 | |
| }, | |
| "plugin_config": { | |
| "attention_qk_half_accumulation": false, | |
| "bert_attention_plugin": false, | |
| "context_fmha_type": 0, | |
| "gemm_plugin": "float16", | |
| "gpt_attention_plugin": "float16", | |
| "identity_plugin": false, | |
| "in_flight_batching": false, | |
| "inflight_batching_gpt_attention_plugin": false, | |
| "layernorm_plugin": false, | |
| "layernorm_quantization_plugin": false, | |
| "lookup_plugin": false, | |
| "nccl_plugin": false, | |
| "paged_kv_cache": false, | |
| "quantize_per_token_plugin": false, | |
| "quantize_tensor_plugin": false, | |
| "remove_input_padding": false, | |
| "rmsnorm_plugin": false, | |
| "rmsnorm_quantization_plugin": false, | |
| "smooth_quant_gemm_plugin": false, | |
| "weight_only_groupwise_quant_matmul_plugin": false, | |
| "weight_only_quant_matmul_plugin": false | |
| } | |
| } | |