metal : add set_rows with f16 src0 - #25434
Merged
Merged
Conversation
ggerganov
approved these changes
Jul 8, 2026
ggerganov
added a commit
that referenced
this pull request
Jul 8, 2026
ggerganov
added a commit
that referenced
this pull request
Jul 10, 2026
CowboyTim
pushed a commit
to aardbeiplantje/llama.cpp
that referenced
this pull request
Jul 21, 2026
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
gianni-cor
pushed a commit
to tetherto/qvac-fabric-llm.cpp
that referenced
this pull request
Jul 25, 2026
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
ggerganov
added a commit
that referenced
this pull request
Jul 28, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
This PR adds support for Metal GGML_OP_SET_ROWS where
src0type is f16 anddsttype is also f16. This will come in handy in models based on DeepSeek Sparse Attention (DeepSeek V3.2, V4, GLM 5.0, 5.1, 5.2) where we have to "sparsify" KQ mask based on lightning indexer indices. With f16 support in GGML_OP_SET_ROWS it will be possible to use f16 FA KQ masks without any extra casts, this will reduce memory usage and simplify code.Additional information
Used @ggerganov code as discussed in #25370
Requirements