Repository navigation
Conversation
kshyatt
marked this pull request as ready for review
November 6, 2026 17:27
Codecov Report❌ Patch coverage is
🚀 New features to boost your workflow:
|
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Right now we're doing a roundtrip when we normalize a tensor backed by a GPU array, because
normreturns a host scalar which is then copied back to the GPU for the actual normalization. This is synchronizing also. I added some generic fallbacks as well as a hook for the 2-norm since some benchmarking showed thatcuBLAS.nrm2is ~6x as fast as my fallback and avoids overflows. Once a new AMDGPU is out we can supportrocBLAS.nrm2also.