Skip to content

Add sgl dsv4 gb300 1k1k disagg non-mtp configs#161

Open
akhilg-nv wants to merge 1 commit into
NVIDIA:mainfrom
akhilg-nv:dsv4-gb300-1k1k
Open

Add sgl dsv4 gb300 1k1k disagg non-mtp configs#161
akhilg-nv wants to merge 1 commit into
NVIDIA:mainfrom
akhilg-nv:dsv4-gb300-1k1k

Conversation

@akhilg-nv
Copy link
Copy Markdown

No description provided.

@codecov-commenter
Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (main@69d04b2). Learn more about missing BASE report.

Additional details and impacted files
@@           Coverage Diff           @@
##             main     #161   +/-   ##
=======================================
  Coverage        ?   65.07%           
=======================================
  Files           ?       67           
  Lines           ?     8214           
  Branches        ?        0           
=======================================
  Hits            ?     5345           
  Misses          ?     2869           
  Partials        ?        0           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Copy link
Copy Markdown
Collaborator

@YAMY1234 YAMY1234 left a comment

Choose a reason for hiding this comment

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

Thanks! Could you please help clean it up by removing the comments, the container names( maybe rename it to a normal name like dev-cu13 since we are using tot main for submission in the future), and the extra mounts? and cluster node name and any other stuff you think are not needed

@weireweire
Copy link
Copy Markdown
Collaborator

FYI, I'll add the 8k1k config. (https://github.com/NVIDIA/srt-slurm/pull/130/changes) It would be better to use zip_override to avoid dup config items.

yhyang201 added a commit to SemiAnalysisAI/InferenceX that referenced this pull request May 22, 2026
Port 9 non-MTP disagg configs from NVIDIA/srt-slurm#161:
- 1p1d dep8/dep16, 1p4d, 1p6d, 2p1d dep12/dep16/dep48
- low-latency dep4/tp4 with zip overrides
yhyang201 added a commit to SemiAnalysisAI/InferenceX that referenced this pull request Jun 4, 2026
Port 9 non-MTP disagg configs from NVIDIA/srt-slurm#161:
- 1p1d dep8/dep16, 1p4d, 1p6d, 2p1d dep12/dep16/dep48
- low-latency dep4/tp4 with zip overrides
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants