fix: use --context-length instead of --max-model-len for SGLang server

2026-07-08 07:57:15 +00:00 · 2026-07-08 07:57:15 +00:00 · 3cf8b8f0d7
commit 3cf8b8f0d7
parent 06b3398ad0
1 changed files with 1 additions and 1 deletions
--- 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 \