OpenVINO Backend: Fuse IM2COL + MatMul convolution into OpenVINO convolution - #288
Merged
wine99 merged 1 commit intoAug 19, 2026
Merged
Conversation
mostafafaheem
changed the title
ravi9
force-pushed
the
dev_backend_openvino
branch
from
August 18, 2026 14:43
eb54a50 to
04b5691
Compare
mostafafaheem
force-pushed
the
fuse_to_convolution
branch
from
August 18, 2026 15:08
04eac2d to
fd2169c
Compare
cavusmustafa
approved these changes
Aug 18, 2026
cavusmustafa
left a comment
cavusmustafa
left a comment
Collaborator
There was a problem hiding this comment.
LGTM, seems like the failing CI test not related to PR.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds a transformation pass to bypass GGML's indirect convolution implementation and take advantage of OpenVINO's direct conv kernels, resulting in a ~2x performance improvement on CPU.
Normal:
Fused: