[Kernel] Add dilation, padding_mode and groups to convolution kernel. - #1032
Open
amd-nprotaso wants to merge 36 commits into
Open
[Kernel] Add dilation, padding_mode and groups to convolution kernel.#1032amd-nprotaso wants to merge 36 commits into
amd-nprotaso wants to merge 36 commits into
Conversation
new/old 1.05x 1.06x 1.05x 1.09x 1.02x 1.06x 0.99x 1.03x 1.06x 1.12x 1.13x 1.03x 1.06x 1.12x 1.16x
# Conflicts: # kernels/conv/conv3d_implicit.py # kernels/conv/conv3d_implicit_fp8.py # tests/kernels/test_conv3d_implicit_fp8.py
amd-nprotaso
force-pushed
the
convolution
branch
from
August 19, 2026 17:03
3c3c143 to
7be935f
Compare
coderfeli
reviewed
Aug 20, 2026
coderfeli
reviewed
Aug 20, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
We want to cover all functionality of torch convolution kernel, so we add dilation, padding_mode and groups. Also tune scheduling of kernel to improve performance. In fp8 kernel there are only cosmetic changes, replace old llvm api to new fx operations.
Performance comparison base on Flux kernel calls: