Implementation of tiled attention with bf16 and circular buffers which reduces memory requirements by 4x on longer context on gemma models.#839
Merged
copybara-service[bot] merged 1 commit intodevfrom Feb 24, 2026
Conversation
copybara-service
bot
force-pushed
the
test_864904207
branch
6 times, most recently
from
acf7894 to
239d792
Compare
copybara-service
bot
changed the title
copybara-service
bot
force-pushed
the
test_864904207
branch
from
239d792 to
6de9655
Compare
…h reduces memory requirements by 4x on longer context on gemma models. It also supports better parallelism for small batch sizes / small models. It also is able to utilize VDPBF16PS for nice 2x improvement on avx512 PiperOrigin-RevId: 874517319
copybara-service
bot
force-pushed
the
test_864904207
branch
from
6de9655 to
df162ea
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Implementation of tiled attention with bf16 and circular buffers which reduces memory requirements by 4x on longer context on gemma models.
It also supports better parallelism for small batch sizes / small models.
It also is able to utilize VDPBF16PS for nice 2x improvement on avx512