[CUDA] JIT-compile qmm_naive#3576
Open
zcbenz wants to merge 1 commit into
Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bundle the headers of CUTLASS and JIT-compile the qmm_naive kernels, which reduces the binary size (#3567) and is required for meeting the size limit of PyPI. Most of the changes are moving code to
backend/cuda/deviceand reducing uses of advanced C++ features to make NVRTC happy.An unfortunate side effect is
test_quantized.pynow takes half an hour to run, I will try if I can make some sub-tests run in parallel or do some proper caching in CI.