Skip to content

Update DSv4 GB300 Dynamo SGLang MTP image #1637

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 4 commits into from
Jun 3, 2026
+8 −1
Merged

Update DSv4 GB300 Dynamo SGLang MTP image #1637

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7d27241
chore: update dsv4 gb300 dynamo sglang mtp image
Fridge003 Jun 2, 2026
a2c5d68
chore: log dsv4 gb300 sglang mtp image bump
Fridge003 Jun 2, 2026
3d4b7ea
Merge branch 'main' into codex/sglang-nightly-20260527
Oseltamivir Jun 2, 2026
6ce9969
Merge branch 'main' into codex/sglang-nightly-20260527
Fridge003 Jun 3, 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 .github/configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9067,7 +9067,7 @@ glm5-fp8-b200-dynamo-sglang:

# MTP variant of dsv4-fp4-gb300-dynamo-sglang.
dsv4-fp4-gb300-dynamo-sglang-mtp:
image: lmsysorg/sglang:nightly-dev-cu13-20260509-9ee83034
image: lmsysorg/sglang:nightly-dev-20260527-14f81a67
Copy link
Copy Markdown

@cursor cursor Bot Jun 2, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

MTP image missing cu13 tag for GB300 hardware

High Severity

The image was changed from nightly-dev-cu13-20260509-9ee83034 (CUDA 13) to nightly-dev-20260527-14f81a67 (CUDA 12). SGLang publishes separate nightly-dev-* and nightly-dev-cu13-* variants for CUDA 12 and CUDA 13 respectively. The sibling config dsv4-fp4-gb300-dynamo-sglang on the same gb300-cw runner correctly uses nightly-dev-cu13-20260520-425dffbd. Running a CUDA 12 image on GB300 hardware requiring CUDA 13 will likely cause runtime failures.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit a2c5d68. Configure here.

model: deepseek-ai/DeepSeek-V4-Pro
model-prefix: dsv4
runner: gb300-cw
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 @@ -3404,6 +3404,13 @@
- "Add DeepSeek-V4-Pro FP4 MI355X ATOM MTP3 benchmark; image rocm/atom:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.3"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1627

- config-keys:
- dsv4-fp4-gb300-dynamo-sglang-mtp
description:
- "Update SGLang image from nightly-dev-cu13-20260509-9ee83034 to nightly-dev-20260527-14f81a67"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1637


- config-keys:
- minimaxm2.5-fp4-gb200-dynamo-vllm
description:
Expand Down
Loading