File size: 5,364 Bytes
5c1e562 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 |
{
"version": "0.12.0.dev2024073000",
"pretrained_config": {
"mlp_bias": false,
"attn_bias": false,
"rotary_base": 500000.0,
"rotary_scaling": {
"factor": 8.0,
"low_freq_factor": 1.0,
"high_freq_factor": 4.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"residual_mlp": false,
"disable_weight_only_quant_plugin": false,
"moe": {
"num_experts": 0,
"top_k": 0,
"normalization_mode": null,
"tp_mode": 0
},
"remove_duplicated_kv_heads": false,
"architecture": "LlamaForCausalLM",
"dtype": "bfloat16",
"vocab_size": 128256,
"hidden_size": 4096,
"num_hidden_layers": 24,
"num_attention_heads": 32,
"hidden_act": "silu",
"logits_dtype": "float32",
"norm_epsilon": 1e-05,
"position_embedding_type": "rope_gpt_neox",
"max_position_embeddings": 131072,
"num_key_value_heads": 8,
"intermediate_size": 7168,
"mapping": {
"world_size": 1,
"gpus_per_node": 8,
"cp_size": 1,
"tp_size": 1,
"pp_size": 1,
"moe_tp_size": 1,
"moe_ep_size": 1
},
"quantization": {
"quant_algo": "W8A16",
"kv_cache_quant_algo": null,
"group_size": 128,
"smoothquant_val": null,
"clamp_val": null,
"has_zero_point": false,
"pre_quant_scale": false,
"exclude_modules": null
},
"use_parallel_embedding": false,
"embedding_sharding_dim": 0,
"share_embedding_table": false,
"head_size": 128,
"qk_layernorm": false
},
"build_config": {
"max_input_len": 1024,
"max_seq_len": 4096,
"opt_batch_size": null,
"max_batch_size": 256,
"max_beam_width": 1,
"max_num_tokens": 8192,
"opt_num_tokens": 256,
"max_prompt_embedding_table_size": 0,
"gather_context_logits": false,
"gather_generation_logits": false,
"strongly_typed": true,
"builder_opt": null,
"force_num_profiles": null,
"profiling_verbosity": "layer_names_only",
"enable_debug_output": false,
"max_draft_len": 0,
"speculative_decoding_mode": 1,
"use_refit": false,
"input_timing_cache": null,
"output_timing_cache": "model.cache",
"lora_config": {
"lora_dir": [],
"lora_ckpt_source": "hf",
"max_lora_rank": 64,
"lora_target_modules": [],
"trtllm_modules_to_hf_modules": {}
},
"auto_parallel_config": {
"world_size": 1,
"gpus_per_node": 8,
"cluster_key": "A100-SXM-40GB",
"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*"
],
"fill_weights": false,
"parallel_config_cache": null,
"profile_cache": null,
"dump_path": null,
"debug_outputs": []
},
"weight_sparsity": false,
"weight_streaming": false,
"plugin_config": {
"dtype": "bfloat16",
"bert_attention_plugin": "auto",
"gpt_attention_plugin": "bfloat16",
"gemm_plugin": "bfloat16",
"gemm_swiglu_plugin": null,
"fp8_rowwise_gemm_plugin": null,
"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": "bfloat16",
"quantize_per_token_plugin": false,
"quantize_tensor_plugin": false,
"moe_plugin": "auto",
"mamba_conv1d_plugin": "auto",
"context_fmha": true,
"context_fmha_fp32_acc": false,
"paged_kv_cache": true,
"remove_input_padding": true,
"reduce_fusion": false,
"enable_xqa": true,
"tokens_per_block": 64,
"use_paged_context_fmha": false,
"use_fp8_context_fmha": false,
"multiple_profiles": false,
"paged_state": true,
"streamingllm": false
},
"use_strip_plan": false,
"max_encoder_input_len": 1024,
"use_fused_mlp": false
}
} |