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

make llama V2 work on more backends with a new parameter --backend #400

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

foldl
Copy link

@foldl foldl commented Jul 19, 2023

With this PR, backend can be set through command line option --backend, which defaults to CUDA.

One can test V2 model (at least 7B) on CPU.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jul 19, 2023
Copy link

@auxon auxon left a comment

Choose a reason for hiding this comment

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

The updated README.md says to use --device but the code expects --backend.

@foldl foldl requested a review from auxon July 20, 2023 03:20
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants