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

Issues with the effectiveness of W4A16 quantization using AWQ #157

Open
RanchiZhao opened this issue Dec 10, 2024 · 0 comments
Open

Issues with the effectiveness of W4A16 quantization using AWQ #157

RanchiZhao opened this issue Dec 10, 2024 · 0 comments

Comments

@RanchiZhao
Copy link

For quantizing the llm part of VILA, I would like to know why AWQ was chosen instead of GPTQ. Have you tried using GPTQ to quantize the LLM part? AWQ performs better?
gheinrich pushed a commit to gheinrich/VILA that referenced this issue Dec 16, 2024
@Qinghao-Hu
Add ZigzagRing Support (NVlabs#157)
118c349
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
1 participant
@RanchiZhao