config.json

{
    "version": "0.11.0.dev2024061800",
    "pretrained_config": {
        "architecture": "BloomForCausalLM",
        "dtype": "float16",
        "vocab_size": 250880,
        "hidden_size": 1024,
        "num_hidden_layers": 24,
        "num_attention_heads": 16,
        "hidden_act": "gelu",
        "logits_dtype": "float32",
        "norm_epsilon": 1e-05,
        "position_embedding_type": "alibi",
        "max_position_embeddings": null,
        "num_key_value_heads": 16,
        "intermediate_size": 4096,
        "mapping": {
            "world_size": 2,
            "gpus_per_node": 8,
            "tp_size": 2,
            "pp_size": 1,
            "moe_tp_size": 2,
            "moe_ep_size": 1
        },
        "quantization": {
            "quant_algo": null,
            "kv_cache_quant_algo": null,
            "group_size": 128,
            "smoothquant_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": 64,
        "qk_layernorm": false
    },
    "build_config": {
        "max_input_len": 1024,
        "max_seq_len": 2048,
        "opt_batch_size": null,
        "max_batch_size": 64,
        "max_beam_width": 1,
        "max_num_tokens": 8192,
        "opt_num_tokens": 64,
        "max_prompt_embedding_table_size": 0,
        "gather_context_logits": false,
        "gather_generation_logits": false,
        "strongly_typed": true,
        "builder_opt": 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-80GB",
            "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": "float16",
            "bert_attention_plugin": "auto",
            "gpt_attention_plugin": "auto",
            "gemm_plugin": "float16",
            "gemm_swiglu_plugin": null,
            "smooth_quant_gemm_plugin": null,
            "identity_plugin": null,
            "layernorm_quantization_plugin": null,
            "rmsnorm_quantization_plugin": null,
            "nccl_plugin": "float16",
            "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": "auto",
            "mamba_conv1d_plugin": "auto",
            "context_fmha": true,
            "context_fmha_fp32_acc": false,
            "paged_kv_cache": true,
            "remove_input_padding": true,
            "use_custom_all_reduce": true,
            "reduce_fusion": false,
            "multi_block_mode": false,
            "enable_xqa": true,
            "attention_qk_half_accumulation": false,
            "tokens_per_block": 64,
            "use_paged_context_fmha": true,
            "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
    }
}