Refactor and optimize the LHS fused quantized matmul kernel. - #352
Merged
Conversation
copybara-service
Bot
force-pushed
the
test_963038497
branch
2 times, most recently
from
August 13, 2026 18:46
58ed420 to
93e1907
Compare
This change updates the LHS fused quantized matmul kernel to support 1D sub-channel quantization and subtiling. It splits the kernel into specialized single-K and multiple-K execution paths to improve performance. Additionally, the scale tensor layout is simplified from 4D to 2D, the quantization helper is updated to support axis-wise quantization using jnp.rint, and support for custom quantization functions is introduced. PiperOrigin-RevId: 964208286
copybara-service
Bot
force-pushed
the
test_963038497
branch
from
August 13, 2026 18:47
93e1907 to
aa623ac
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Refactor and optimize the LHS fused quantized matmul kernel.
This change updates the LHS fused quantized matmul kernel to support 1D sub-channel quantization and subtiling. It splits the kernel into specialized single-K and multiple-K execution paths to improve performance. Additionally, the scale tensor layout is simplified from 4D to 2D, the quantization helper is updated to support axis-wise quantization using jnp.rint, and support for custom quantization functions is introduced.