[Build/CI][DP/EP] Add QWen/Qwen3-30B-A3B-FP8 + EPLB tests to Nightly H100 and B200 #29195
+19
−6
Conversation
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
Contributor
Author
|
cc @robertgshaw2-redhat @mgoin @tlrmchlsmth . PTAL 🤚 |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request enables EPLB for QWen/Qwen3-30B-A3B-FP8 in nightly tests on H100 and adds a new, similar test for B200. The changes are functionally correct and achieve the stated goal. I have one suggestion to improve the maintainability of the Buildkite pipeline configuration by reducing duplication between the H100 and B200 test jobs.
mgoin
reviewed
Nov 21, 2025
added 3 commits
November 21, 2025 19:32
Signed-off-by: Varun Sundar Rabindranath <[email protected]>
Signed-off-by: Varun Sundar Rabindranath <[email protected]>
Signed-off-by: Varun Sundar Rabindranath <[email protected]>
varun-sundar-rabindranath
force-pushed
the
varun/add-qwen-eplb-test
branch
from
c4eca46 to
8a1d253
Compare
| num_gpus: 2 | ||
| working_dir: "/vllm-workspace" | ||
| commands: | ||
| - bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020 2 1 |
Contributor
Author
There was a problem hiding this comment.
dp-size = 2 and tp-size 1
| working_dir: "/vllm-workspace" | ||
| commands: | ||
| - bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep.sh 0.8 200 8020 | ||
| - bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020 |
Contributor
Author
There was a problem hiding this comment.
dp-size=2 tp-size=2
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.
Purpose
Enable EPLB for
QWen/Qwen3-30B-A3B-FP8H100 Nightly tests. Add this test to B200 nightly as well.QWen/Qwen3-30B-A3B-FP8closely mirrors DeepSeek block FP8 models. This is useful so we can catch bugs like #29162 early.Test Plan
Run
.buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.shscript locally on B200.Test Result
Test passes with fix #29162