musa: workaround for Guilty Lockup in cleaning src0 in #10032 #10042
Conversation
This file contains 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: Xiaodong Ye <xiaodong.ye@mthreads.com>
yeahdongcn
force-pushed
the
mtgpu_guilty_lockup
branch
from
1001967
to
862b959
Compare
|
Could you please review this PR? I know the code looks ugly, but it works for now. |
JohannesGaessler
approved these changes
Oct 28, 2024
Yes. After reviewing all contexts, this approach appears to be the only viable solution to avoid a crash. Thanks for approving this! |
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 15, 2024
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 18, 2024
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
We’re encountering an MTGPU Guilty Lockup issue during the model warm-up stage after merging #10032. This PR reverts this change for MUSA only.
I've raised an internal issue and will remove this workaround once it has been resolved.