ggml-metal: fix bf16/f16 matmul kernels #18210
Open
+11
−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
Ensure bf16/f16 cooperative tensor paths use matching compute types. Add bf16/f16 mul_mat coverage and allow CPU reference for mul_mat_id.
github-actions
bot
added
testing
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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 #17986.
Use half compute types for bf16/f16 cooperative tensor matmul to avoid Metal compile failures.
Add bf16/f16 mul_mat + mul_mat_id coverage and allow CPU reference for mul_mat_id.
Testing: ctest --test-dir build -R test-backend-ops --output-on-failure