wget -O question.jsonl https://raw.githubusercontent.com/lm-sys/FastChat/main/fastchat/llm_judge/data/mt_bench/question.jsonl
python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
python3 bench_sglang.py --num-questions 80
python3 -m vllm.entrypoints.api_server --tokenizer-mode auto --model meta-llama/Llama-2-7b-chat-hf --disable-log-requests --port 21000
python3 bench_other.py --num-questions 80 --backend vllm
# A10G
python -m lightllm.server.api_server --tokenizer_mode auto --model_dir ~/model_weights/llama-2-7b-chat-hf --max_total_token_num 16000 --port 22000
python3 bench_other.py --num-questions 80 --backend lightllm