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

[FEATURE] Backport vllm expanded Marlin kernel to autogptq. #653

Open
Qubitium opened this issue Apr 27, 2024 · 1 comment
Open

[FEATURE] Backport vllm expanded Marlin kernel to autogptq. #653

Qubitium opened this issue Apr 27, 2024 · 1 comment

Comments

@Qubitium
Copy link
Contributor

Qubitium commented Apr 27, 2024 •
edited

PR: vllm-project/vllm#3922

  • Adds support for more group sizes
  • Adds support for desc_act=True (activation reordering)
@Qubitium Qubitium changed the title [Feature] Backport vllm expanded Marlin kernel to autogptq. [FEATURE] Backport vllm expanded Marlin kernel to autogptq. Apr 27, 2024
@Qubitium Qubitium mentioned this issue Apr 27, 2024
Open
@qwopqwop200
Copy link
Collaborator

This new Marlin kernel looks good.
I'll start working on it tomorrow if I have time.

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

No branches or pull requests
2 participants
@Qubitium @qwopqwop200