diff --git a/experiments/dsv4_h200_sglang_vs_vllm/start_sglang.sh b/experiments/dsv4_h200_sglang_vs_vllm/start_sglang.sh index 0bc7777..89fc7de 100755 --- a/experiments/dsv4_h200_sglang_vs_vllm/start_sglang.sh +++ b/experiments/dsv4_h200_sglang_vs_vllm/start_sglang.sh @@ -44,7 +44,7 @@ nohup sglang serve \ --model-path "$MODEL_PATH" \ --tp "$TP" \ --moe-runner-backend marlin \ - --max-model-len "$MAX_MODEL_LEN" \ + --context-length "$MAX_MODEL_LEN" \ --max-running-requests "$MAX_RUNNING" \ --mem-fraction-static 0.88 \ --host 0.0.0.0 \