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

Any plan about W4A8 #873

Open
Arcmoon-Hu opened this issue Oct 29, 2024 · 2 comments
Open

Any plan about W4A8 #873

Arcmoon-Hu opened this issue Oct 29, 2024 · 2 comments
Labels
enhancement New feature or request

Comments

@Arcmoon-Hu
Copy link

Any plan about W4A8？
@Arcmoon-Hu Arcmoon-Hu added the enhancement New feature or request label Oct 29, 2024
@robertgshaw2-neuralmagic
Copy link
Collaborator

Did you run into an issue using this in llm-compressor?

We are working on extending the machete kernels in vllm to support W4A8 and will hook up the compressed-tensors models once this is complete.

@RameshArvind
Copy link

Are you suggesting that W4A8 already works in llm-compressor? Like if we pass the scheme=W4A8 here in this example this will work? An example recipe would be great if so!

Couldn't find an example

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@RameshArvind @Arcmoon-Hu @robertgshaw2-neuralmagic