Skip to content
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

[PIR][OneDNN] Support Split op in bf16 (do not merge, need check ci coverage) #70857

Merged

Conversation

zhanglirong1999
Copy link
Contributor

@zhanglirong1999 zhanglirong1999 commented Jan 16, 2025

PR Category

Inference

PR Types

Performance

Description

Split op output is a vector, and not support bf16 q/dq in the past. We support Split op in bf16 now. We support two patterns for split op. split + builtin.split and split + builtin.slice pattern

@zhanglirong1999 zhanglirong1999 changed the title [PIR][OneDNN] Support Split op in bf16 (do not merge, just test ci coverage) [PIR][OneDNN] Support Split op in bf16 (do not merge, need check ci coverage) Jan 16, 2025
@paddle-bot paddle-bot bot added the contributor External developers label Jan 16, 2025
Copy link
Contributor

@LLee233 LLee233 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The 2nd pattern should be similar.

@zhanglirong1999 zhanglirong1999 force-pushed the split_bf16_support branch 4 times, most recently from 9b4d533 to 7f3382e Compare January 21, 2025 12:11
Copy link
Contributor

@LLee233 LLee233 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@zhanglirong1999 zhanglirong1999 merged commit 0dc0c49 into PaddlePaddle:develop Jan 22, 2025
32 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
contributor External developers Intel
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants