Modernize Pallas Splash attention kernel and define eager fallback routing in Tunix Gemma 4. - #1890
Merged
Merged
Conversation
copybara-service
Bot
requested review from
abheesht17,
hgao327,
jiangyangmu,
lc5211,
s-noghabi,
sizhit2,
tianshub and
wang2yn84
as code owners
August 14, 2026 12:03
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 14, 2026 14:34
8427f88 to
6cbfdfa
Compare
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 15, 2026 08:34
6cbfdfa to
d48cbd0
Compare
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 15, 2026 13:26
d48cbd0 to
055281a
Compare
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 15, 2026 13:58
055281a to
a9eacb8
Compare
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 18, 2026 08:25
a9eacb8 to
3f67ddb
Compare
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 18, 2026 16:31
3f67ddb to
1b0a047
Compare
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 19, 2026 10:07
1b0a047 to
c23a14d
Compare
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 20, 2026 22:36
c23a14d to
33925ee
Compare
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 25, 2026 08:46
33925ee to
219ef36
Compare
…uting in Tunix Gemma 4. - Refactor Attention.block() into modular helper methods. - Broaden Pallas Splash attention execution across rectangular sequences (kv_len > q_len) using memoized in-kernel computable masks (LocalMask / CausalMask). - Define eager attention fallback routing (_eager_attention) with exact offset alignment for rectangular sequences. - Modernize use_gqa property to properly support MQA (num_kv_heads=1). - Add unit tests for mask predicate equivalence, block-size divisibility, and attention routing. PiperOrigin-RevId: 970406871
copybara-service
Bot
force-pushed
the
test_963446160
branch
from
August 25, 2026 09:18
219ef36 to
cbcfa7f
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
2 participants
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.
Modernize Pallas Splash attention kernel and define eager fallback routing in Tunix Gemma 4.