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

Insitu quantization OOM for large models #344

Closed
nidhoggr-nil opened this issue May 23, 2024 · 2 comments
Closed

Insitu quantization OOM for large models #344

nidhoggr-nil opened this issue May 23, 2024 · 2 comments
Labels
bug Something isn't working

Comments

@nidhoggr-nil
Copy link

Describe the bug
quantizing large models via insitu quantization leads to out of memory issues even though the quantized final version should be able to fit in vram.

Latest commit
ac5dd0f
@nidhoggr-nil nidhoggr-nil added the bug Something isn't working label May 23, 2024
@EricLBuehler EricLBuehler mentioned this issue May 26, 2024
Merged
@EricLBuehler
Copy link
Owner

Hi @nidhoggr-nil!

I just merged #346, which enables loading of ISQ on the CPU. Can you please confirm that it works for you?

@EricLBuehler
Copy link
Owner

Closing as resolved.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@nidhoggr-nil @EricLBuehler