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

[SYCL] Add freq factors support to sycl rope operation #7495

Merged
merged 1 commit into from
May 27, 2024

Conversation

AidanBeltonS
Copy link
Contributor

This PR adds support for freq factors for the ROPE operation. The approach is based on the CUDA implementation.

All rope tests are passing on intel PVC and Nvidia A100 for the SYCL backend.

@github-actions github-actions bot added the SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language label May 23, 2024
@mofosyne mofosyne added the Review Complexity : High Generally require indepth knowledge of LLMs or GPUs label May 23, 2024
Copy link
Collaborator

@NeoZhangJianyu NeoZhangJianyu left a comment

Choose a reason for hiding this comment

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

The UT case of ROPE are passed on Arc 770.
It's good!

@characharm
Copy link

Phi-3-medium-128k-instruct-Q8_0.gguf works fine

Copy link
Collaborator

@abhilash1910 abhilash1910 left a comment

Choose a reason for hiding this comment

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

LGTM!

@abhilash1910 abhilash1910 merged commit 5487593 into ggerganov:master May 27, 2024
65 checks passed
@AidanBeltonS AidanBeltonS deleted the add_freq_factors branch May 27, 2024 13:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Review Complexity : High Generally require indepth knowledge of LLMs or GPUs SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants