CUDA: fix bug in rms_norm fusion #15660
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
github-actions
bot
added
Nvidia GPU
JohannesGaessler
approved these changes
Aug 29, 2025
|
@am17an Try just |
ggml-ci
am17an
force-pushed
the
fix_rms_norm_add
branch
from
5121760 to
28fc7cc
Compare
|
For |
Ahhh. |
|
The code that triggers the CI is at https://github.com/ggml-org/ci/blob/master/run.sh. It shouldn't be too hard to modify it to monitor all the branches in pull requests using the github API. |
|
Since we can't test the ggml-ci right away, I will proceed to merge this since it fixes some bugs in master. |
qnixsynapse
pushed a commit
to janhq/llama.cpp
that referenced
this pull request
Aug 30, 2025
* CUDA: fix bug in rms_norm fusion * Fix bug for OP_REPEAT * Fix index for add
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Outdated suggestions cannot be applied.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 bugs pointed out by @ORippler and @CISC in #15631
dst->src[I+1], whereas in repeat we only have 1 src