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.

Sign up for GitHub

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

Jump to bottom

[transformer] add rope for transformer/conformer #2458

Merged
merged 8 commits into from
Apr 4, 2024
Merged

[transformer] add rope for transformer/conformer #2458

merged 8 commits into from
Apr 4, 2024

Conversation

Mddct
Copy link
Collaborator

@Mddct Mddct commented Apr 3, 2024 •
edited
Loading

#2363

TODO:

  • aishell benchmark

BTW: 目前实现不支持transformer decoder+rope

  • decoder + rope 性能会降低
  • llm 大多是为decoder only架构， 不需要cross att 的cache

@Mddct Mddct mentioned this pull request Apr 3, 2024
Open
9 tasks
@Mddct
Copy link
Collaborator Author

Mddct commented Apr 4, 2024 •
edited
Loading

rope性能和三角pos保持一致
#2363 (comment)

截屏2024-04-04 09 56 25 截屏2024-04-04 09 56 14

@Mddct Mddct requested review from xingchensong and robin1001 April 4, 2024 01:56
@xingchensong xingchensong merged commit 4d12918 into main Apr 4, 2024
6 checks passed
@xingchensong xingchensong deleted the Mddct-rope branch April 4, 2024 02:03
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@xingchensong xingchensong xingchensong approved these changes

@robin1001 robin1001 Awaiting requested review from robin1001

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@Mddct @xingchensong