qqtang/sskj
1
2
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
yy-fighting 2026-07-08 07:57:15 +00:00
parent 06b3398ad0
commit 3cf8b8f0d7
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
experiments/dsv4_h200_sglang_vs_vllm/start_sglang.sh
View File

@ -44,7 +44,7 @@ nohup sglang serve \
--model-path "$MODEL_PATH" \ --model-path "$MODEL_PATH" \
--tp "$TP" \ --tp "$TP" \
--moe-runner-backend marlin \ --moe-runner-backend marlin \
--max-model-len "$MAX_MODEL_LEN" \ --context-length "$MAX_MODEL_LEN" \
--max-running-requests "$MAX_RUNNING" \ --max-running-requests "$MAX_RUNNING" \
--mem-fraction-static 0.88 \ --mem-fraction-static 0.88 \
--host 0.0.0.0 \ --host 0.0.0.0 \