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

H100 Adaptability #273

Closed
wants to merge 3 commits into from
Closed

H100 Adaptability #273

wants to merge 3 commits into from

Conversation

FortuneBush
Copy link
Contributor

int8 is not suitable for H100 device when using bitsandbytes.
So I add an judgment to automatically set the precision value.
Hoping you can receive! Thanks!!! @yezhengmao1
image

@yezhengmao1
Copy link
Collaborator

you can load the model by passing the argument like --precision nf4.

your change will make all the H100 load the model in nf4 precision?

@FortuneBush
Copy link
Contributor Author

yes! I add a process to judge if it is H100 device.

@yezhengmao1
Copy link
Collaborator

yes! I add a process to judge if it is H100 device.

can you close the pr, if it works fine.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants