[BugFix] Fix assert in build_for_cudagraph_capture
#29893
Merged
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
Signed-off-by: Lucas Wilkinson <[email protected]>
LucasWilkinson
changed the title
build_for_cudagraph_capture
Collaborator
Author
|
Confirmed fixed by @varun-sundar-rabindranath |
Contributor
|
I was hitting this assert #29852 on DP/EP on the Decode nodes in a PD setup. I no longer hit this assert with this PR. |
LucasWilkinson
added
the
ready
LucasWilkinson
changed the title
build_for_cudagraph_capturebuild_for_cudagraph_capture
tlrmchlsmth
approved these changes
Dec 2, 2025
khluu
pushed a commit
that referenced
this pull request
Dec 3, 2025
Signed-off-by: Lucas Wilkinson <[email protected]> (cherry picked from commit 5cdd664)
minosfuture
added a commit
to minosfuture/vllm
that referenced
this pull request
Dec 4, 2025
…oject#29893)" This reverts commit 5cdd664.
charlotte12l
pushed a commit
to charlotte12l/vllm
that referenced
this pull request
Dec 5, 2025
) Signed-off-by: Lucas Wilkinson <[email protected]> Signed-off-by: Xingyu Liu <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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.
FIX: #29852
Make sure we only call
build_for_cudagraph_captureif we are capturing cudagraphs not for DP dummy runs; this behavior; NOTE prior to #28579 we used always calledbuild_for_cudagraph_capturefor all dummy runs including DP dummy batches (this was a bit messy), this shouldn't be the case anymore since we build with padding which can cause asserts inbuild_for_cudagraph_captureSigned-off-by: Lucas Wilkinson [email protected]