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

量化相关接口(如weight_dequantize等)支持 group_size == 32 #69977

Open
Aganlengzi opened this issue Dec 5, 2024 · 0 comments
Open

量化相关接口(如weight_dequantize等)支持 group_size == 32 #69977

Aganlengzi opened this issue Dec 5, 2024 · 0 comments
Assignees
@yuanlehome
Labels
status/new-issue 新建 type/feature-request 新需求申请

Comments

@Aganlengzi
Copy link
Contributor

Aganlengzi commented Dec 5, 2024 •
edited
Loading

需求描述 Feature Description

任务目标：支持新硬件SDAA(太初)上量化推理;
需求场景：支持group_size=32的量化;
功能描述：飞桨已有-1,64和128支持，额外加上32支持即可

image

附：希望实现上考虑custom device

替代实现 Alternatives

无
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@yuanlehome yuanlehome

Labels
status/new-issue 新建 type/feature-request 新需求申请
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@Aganlengzi @yuanlehome @chen2016013