Skip to content

[Klaud Cold] Update dsr1-fp8-mi325x-sglang-mtp SGLang ROCm image to v0.5.19-rocm700-mi30x / 将 dsr1-fp8-mi325x-sglang-mtp 的 SGLang ROCm 镜像更新至 v0.5.19-rocm700-mi30x #2844

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

Draft
Klaud-Cold wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

[Klaud Cold] Update dsr1-fp8-mi325x-sglang-mtp SGLang ROCm image to v0.5.19-rocm700-mi30x / 将 dsr1-fp8-mi325x-sglang-mtp 的 SGLang ROCm 镜像更新至 v0.5.19-rocm700-mi30x #2844

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
9704504
chore(amd): update dsr1-fp8-mi325x-sglang-mtp image to v0.5.19-rocm70…
claude[bot] Sep 5, 2026
1fceee6
chore(changelog): add dsr1-fp8-mi325x-sglang-mtp v0.5.19 image entry
claude[bot] Sep 5, 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 configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1286,7 +1286,7 @@ dsv4-fp4-mi355x-atom-mtp:
# works only because it's non-MTP (no draft KV layer). MTP stays tp8-only.

dsr1-fp8-mi325x-sglang-mtp:
image: lmsysorg/sglang:v0.5.12-rocm700-mi30x
image: lmsysorg/sglang:v0.5.19-rocm700-mi30x
model: deepseek-ai/DeepSeek-R1-0528
model-prefix: dsr1
runner: mi325x
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 @@ -6902,3 +6902,9 @@
- "Lower mem-fraction-static from 0.89 to 0.86 on every arm: TP4, TP8 and TP8 with DP attention. swa-full-tokens-ratio becomes per-arm: 0.10 on the tensor-parallel arms as before, 0.15 under DP attention."
- "Drop concurrency 2 and 10 from the TP4 arm, leaving [1, 4, 8], and drop concurrency 16 from the TP8 hicache arm, leaving [32, 48]. Concurrency 16 remains on the TP8 no-offload arm."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2800

- config-keys:
- dsr1-fp8-mi325x-sglang-mtp
description:
- "Update SGLang image from v0.5.12-rocm700-mi30x to v0.5.19-rocm700-mi30x"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2844