Skip to content

[AMD/Hyperloom] Tune dsr1-fp8-mi355x-sglang: --num-continuous-decode-steps 4 → 8 #1243

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

Open
lishuoshuo-amd wants to merge 8 commits into
base: main
Choose a base branch
from
+8 −2
Open

[AMD/Hyperloom] Tune dsr1-fp8-mi355x-sglang: --num-continuous-decode-steps 4 → 8 #1243

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
e7b0fc3
[AMD/Hyperloom] Tune dsr1-fp8-mi355x-sglang: --num-continuous-decode-…
lishuoshuo-amd Apr 21, 2026
b10c872
fix: update dsr1_fp8_mi355x
lishuoshuo-amd Apr 22, 2026
81f861f
fix: update changelog PR link
lishuoshuo-amd May 1, 2026
3f7c353
Merge remote-tracking branch 'origin/main' into amd/hyperloom/mi355x-…
lishuoshuo-amd May 1, 2026
f13cd18
fix: append changelog entry
lishuoshuo-amd May 1, 2026
bf3d59f
chore: trigger sweep
lishuoshuo-amd May 1, 2026
42330f5
Merge remote-tracking branch 'origin/main' into amd/hyperloom/mi355x-…
lishuoshuo-amd May 1, 2026
c709a29
Merge branch 'main' into amd/hyperloom/mi355x-tune-dsr1
chunfangamd May 1, 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/dsr1_fp8_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ python3 -m sglang.launch_server \
--trust-remote-code \
--chunked-prefill-size 196608 \
--mem-fraction-static 0.8 --disable-radix-cache \
--num-continuous-decode-steps 4 \
--num-continuous-decode-steps 8 \
--max-prefill-tokens 196608 \
--kv-cache-dtype fp8_e4m3 \
--cuda-graph-max-bs "$CONC" $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
Expand Down
8 changes: 7 additions & 1 deletion perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2061,7 +2061,13 @@
- "Add TP=4, concurrency 4-256 for 1k1k and 8k1k sequence lengths"
- "Add --gpu-memory-utilization 0.9 to server launch"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1126


- config-keys:
- dsr1-fp8-mi355x-sglang
description:
- "Tune --num-continuous-decode-steps 4 → 8 (+4.7% avg output throughput gain)"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1243

- config-keys:
- dsv4-fp4-gb200-dynamo-vllm-mtp2
description:
Expand Down
Loading