-
Notifications
You must be signed in to change notification settings - Fork 3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[DSK] Implement mla use matrix-absorption #9875
base: develop
Are you sure you want to change the base?
Conversation
Thanks for your contribution! |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #9875 +/- ##
===========================================
- Coverage 51.66% 51.23% -0.43%
===========================================
Files 739 745 +6
Lines 117426 118834 +1408
===========================================
+ Hits 60668 60886 +218
- Misses 56758 57948 +1190 ☔ View full report in Codecov by Sentry. |
818cd29
to
5b45565
Compare
5b45565
to
7ec7f02
Compare
// float in_scale, | ||
// bool causal, | ||
// cudaStream_t &stream, | ||
// paddle::Tensor *out); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这个文件里除了 MLA decode attention之外,还是支持 GQA/MHA 吗?
fix write cache
fix mla_atn
fix mla precision
fix MLA && trick avoid append_dec
lizhenyu04 seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
optimize mla
set kv_cache's bsz=1
03d6a0b
to
2fb3378
Compare
Before submitting
tests
folder. If there are codecov issues, please add tests cases first.PR types
Performance optimization
PR changes
Others
Description