工作常用命令记录--sglang
sglang操作记录 python -m sglang.launch_server \--model-path Qwen/Qwen3-8B \--speculative-algorithm DFLASH \--speculative-draft-model-path z-lab/Qwen3-8B-DFlash-b16 \--speculative-num-draft-tokens 16 \--tp-size 1 \--attention-backend flashinfer \--mem-fract…
2026/7/3 6:49:17