Add gather_qqmm#3757
Open
zcbenz wants to merge 3 commits into
Open
Conversation
zcbenz
force-pushed
the
qmm-global-scale
branch
2 times, most recently
from
f8a6d7d to
ca36a2d
Compare
zcbenz
force-pushed
the
qmm-global-scale
branch
2 times, most recently
from
0cb1b35 to
b396742
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add a simple
gather_qqmmimplementation, by supporting global scale inqmmkernels and use them as fallback.The implementation is bare minimum, for CUDA it is rerouted to
qmm_naiveand for Metal it isqmv. We will add global scale support to moreqmmkernels in followup PRs, and will have specialized fast kernels in future. This PR mostly serves as a way for users to useqqmmbefore we have the native kernels ready.Support for CPU backend is lacked at the moment..