Add Metal support for GGML_OP_DIAG_MASK_INF for CLIP on Apple GPUs #1395
+120
−0
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
…ence on Apple GPUs
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Outdated suggestions cannot be applied.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.
Summary
Add a Metal implementation of
GGML_OP_DIAG_MASK_INFso the op can run on Apple GPUs.Details
Previously, the Metal backend didn't support
GGML_OP_DIAG_MASK_INF, which caused models using this op to fail with:For example,
stable-diffusion.cpp’s SDXL CLIP path could not run withkeep_clip_on_cpu = falseon Metal.This PR:
GGML_OP_DIAG_MASK_INFmatching the existing CPU/CUDA semantics.ggml-metaldispatch so attention masks are applied correctly for batched tensors on Apple GPUs.Related: leejet/stable-diffusion.cpp#1040