Skip to content

dsv4-fp4 sglang b300: floor --max-running-requests at 8 #1173

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Qiaolin-Yu merged 3 commits into from
Apr 26, 2026
Merged

dsv4-fp4 sglang b300: floor --max-running-requests at 8 #1173

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
358e17b
dsv4-fp4 sglang b200/b300: floor --max-running-requests at 8
sglang-bot Apr 26, 2026
90faa53
perf-changelog: add entry for #1173 (max-running-requests floor)
sglang-bot Apr 26, 2026
e0f0c32
revert b200 change; scope to b300 only
sglang-bot Apr 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion benchmarks/single_node/dsv4_fp4_b300_sglang.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,7 @@ PYTHONNOUSERSITE=1 sglang serve \
--port $PORT \
--trust-remote-code \
--tp $TP \
--max-running-requests "$((CONC * 3 / 2))" \
--max-running-requests "$(( CONC * 3 / 2 > 8 ? CONC * 3 / 2 : 8 ))" \
--mem-fraction-static "$MEM_FRACTION_STATIC" \
--swa-full-tokens-ratio "$SWA_FULL_TOKENS_RATIO" \
"${PARALLEL_ARGS[@]}" $EVAL_CONTEXT_ARGS >> $SERVER_LOG 2>&1 &
Expand Down
6 changes: 6 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1862,3 +1862,9 @@
- "Restore the recipe-per-CONC split (low-latency / balanced / max-throughput) on top of the low-latency-only fallback from #1143; the DeepEP FP8 weight-postprocess path is fixed, so the high-throughput scenario runs again"
- "Recipes from https://docs.sglang.io/cookbook/autoregressive/DeepSeek/DeepSeek-V4"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1158

- config-keys:
- dsv4-fp4-b300-sglang
description:
- "Floor --max-running-requests at 8 in dsv4_fp4_b300_sglang.sh so low-CONC sweeps don't drop below the queue depth needed for stable benchmarking (CONC * 3 / 2 still applies above CONC=5)"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1173