Support vLLM DP ranks with tensor-parallel GPU groups#86
Open
nealvaidya wants to merge 2 commits intoNVIDIA:mainfrom
Open
Support vLLM DP ranks with tensor-parallel GPU groups#86nealvaidya wants to merge 2 commits intoNVIDIA:mainfrom
nealvaidya wants to merge 2 commits intoNVIDIA:mainfrom
Conversation
Honor tensor-parallel-size when expanding vLLM data-parallel endpoints so configurations like DP2TP4 launch one process per DP rank with the correct GPU set, while preserving DP16TP1 behavior. Signed-off-by: Neal Vaidya <nealv@nvidia.com>
nealvaidya
requested review from
alec-flowers,
csahithi,
ishandhanani and
nlevin-ui
as code owners
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #86 +/- ##
=======================================
Coverage ? 65.22%
=======================================
Files ? 62
Lines ? 7511
Branches ? 0
=======================================
Hits ? 4899
Misses ? 2612
Partials ? 0 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
tensor-parallel-sizewhen expanding vLLM data-parallel endpoints.Test plan
uv run pytest tests/test_configs.py::TestVLLMDataParallelMode -qMade with Cursor