docker run --rm --network host -v /data:/data -e HF_HUB_OFFLINE=1 -e TRANSFORMERS_OFFLINE=1 --entrypoint python3 local/sglang:kimi-k3-pp-dflash-33863-fi0618-situ4460-kvbounds1 -m sglang.benchmark.serving --backend sglang --host 174.1.60.5 --port 30000 --model /data/hf_models/Kimi-K3 --tokenizer /data/hf_models/Kimi-K3 --dataset-name speed-bench --dataset-path /data/speedbench16k_complete.jsonl --num-prompts 1 --max-concurrency 8 --request-rate 10000 --speed-bench-output-len 1 --temperature 0.0 --top-p 1.0 --seed 42 --warmup-requests 0 --output-details --output-file /data/hzy/sskj/experiments/pro6000/kimi3_pro6000_dp2_nospec_ab/results/dp2-pp8-final-20260902-130711/bench/warm_b.jsonl
