CUDA: fix MMV kernel being used for FP16 src1 #10357
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
ggerganov
approved these changes
Nov 17, 2024
Member
|
Wouldn't it be more reliable to check |
JohannesGaessler
force-pushed
the
cuda-mmv-fixup
branch
from
c527e27 to
5c9e20b
Compare
Collaborator
Author
|
You're right, I forgot to adapt the logic for the first check when I added the variable (already in the previous PR). |
slaren
approved these changes
Nov 17, 2024
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 18, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
Fixes #10356 .
The problem is simply that I forgot to add a check for the type of
src1. While FP16src1is not used for model evaluation it is used in the test code.