-
Notifications
You must be signed in to change notification settings - Fork 139
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
Fix loading of vllm model from files #533
base: main
Are you sure you want to change the base?
Conversation
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Breaks the tests atm
it's weird, we have the same tests fails on lewis' PR I dont get why |
Most likely culprit imo: cb35bea (and the latex2sympy version change) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Very nice feature! Could you add some small doc on how to toggle the params (I know you have the YAML, but having it in the docs would be helpful)
Also, what sampling params are exposed? Is it everything in SamplingParams
or just temperature
and max_tokens
?
Hi ! Sure I will add some docs. |
…ghteval into nathan-fix-vllm-from-file
No description provided.