Skip to content

retrigger mi355x dsv4 #1159

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
Oseltamivir merged 2 commits into from
Apr 25, 2026
Merged

retrigger mi355x dsv4 #1159

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
938d1d0
retrigger mi355x dsv4
Oseltamivir Apr 25, 2026
f660cd2
Refactor changelog descriptions for consistency
Oseltamivir Apr 25, 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
4 changes: 1 addition & 3 deletions benchmarks/single_node/dsv4_fp8_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,13 +83,11 @@ python3 -m sglang.launch_server \
--attention-backend compressed \
--max-running-request 256 \
--page-size 256 \
--chunked-prefill-size 4096 \
--chunked-prefill-size 8192 \
--disable-shared-experts-fusion \
--disable-cuda-graph \
--tool-call-parser deepseekv4 \
--reasoning-parser deepseek-v4 \
--mem-fraction-static 0.88 \
--max-total-tokens $((CONC * (ISL + OSL) + 200)) \
--watchdog-timeout 1800 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &

SERVER_PID=$!
Expand Down
7 changes: 7 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1819,3 +1819,10 @@
- "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/1132

- config-keys:
- dsv4-fp8-mi355x-sglang
description:
- "Drop --mem-fraction-static 0.88 and --max-total-tokens from dsv4_fp8_mi355x.sh"
- "Bump --chunked-prefill-size from 4096 to 8192"
- "Retrigger dsv4-fp8-mi355x-sglang"
Loading