2:4 sparse for int8/fp8/bf16/fp16 gemm#10081
2:4 sparse for int8/fp8/bf16/fp16 gemm#10081zhink wants to merge 8 commits intoPaddlePaddle:developfrom
Conversation
|
Thanks for your contribution! |
Codecov Report✅ All modified and coverable lines are covered by tests. Please upload reports for the commit 34fcbe4 to get more accurate results. ❌ Your project check has failed because the head coverage (46.80%) is below the target coverage (58.00%). You can increase the head coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## develop #10081 +/- ##
===========================================
+ Coverage 46.75% 46.80% +0.04%
===========================================
Files 802 802
Lines 133882 133728 -154
===========================================
- Hits 62603 62594 -9
+ Misses 71279 71134 -145 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
e17eb7f to
2edff4a
Compare
|
This Pull Request is stale because it has been open for 60 days with no activity. 当前Pull Request 60天内无活动,被标记为stale。 |
|
This Pull Request is stale because it has been open for 60 days with no activity. 当前Pull Request 60天内无活动,被标记为stale。 |
Before submitting
testsfolder. If there are codecov issues, please add tests cases first.PR types
New features
PR changes
Others
Description
souport 2:4 sparse mm for int8/fp8/bf16/fp16 gemm,will speed up inference.