Skip to content

Commit

Permalink
Support different dtypes of inputs for broadcast for dropout optimiza…
Browse files Browse the repository at this point in the history 
…tion (PaddlePaddle#52093)

* change judgement for DropoutGradGPUKernelDriver

* add UnrollerWithoutVecSize and after this Loaddata to be refined

* pass unittest

* use same unroller with XPU

* BroadcastWithInt64Index

* BroadcastDataLoader template partial specialization

* fix compile errs in ROCms

* PR comment
  • Loading branch information
@zhangbopd
zhangbopd committed May 9, 2023
1 parent 767e7b3 commit 4938da3
Show file tree
Hide file tree
Showing 4 changed files with 425 additions and 455 deletions.
Loading

0 comments on commit 4938da3

Please sign in to comment.