Add experimental attention quantization flags.#4321
Open
copybara-service[bot] wants to merge 1 commit into
Open
Add experimental attention quantization flags.#4321copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
copybara-service
Bot
requested review from
A9isha,
NicoGrande,
NuojCheng,
RissyRan,
SurbhiJainUSC,
abhinavclemson,
aireenmei,
bvandermoon,
darisoy,
dipannita08,
gagika,
gobbleturk,
hengtaoguo,
igorts-git,
jiangjy1982,
khatwanimohit,
parambole,
richjames0,
shralex,
shuningjin,
suexu1025,
vipannalla and
xibinliu
as code owners
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
This will add two experimental flags to the splash attention config, to quantize Q and K respectively. Attention quantization is currently a research project so these should be turned off by default. In the future we will support more quantization options for the backwards pass, RoPE vs. no-RoPE, more dtypes, etc. PiperOrigin-RevId: 940686402
copybara-service
Bot
force-pushed
the
test_940686402
branch
from
dd302f3 to
9850712
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add experimental attention quantization flags.
This will add two experimental flags to the splash attention config, to
quantize Q and K respectively. Attention quantization is currently a research
project so these should be turned off by default. In the future we will support
more quantization options for the backwards pass, RoPE vs. no-RoPE, more
dtypes, etc.