Skip to content

issue/1001 - feat: add paged attention prefill and decode for moore gpu referencing nvidia #1011

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
Merged
wooway777 merged 2 commits into from
Feb 11, 2026
Merged

issue/1001 - feat: add paged attention prefill and decode for moore gpu referencing nvidia #1011

wooway777 merged 2 commits into from
Feb 11, 2026
+2,068 −0

Conversation

@spike-zhu
Copy link
Contributor

@spike-zhu spike-zhu commented Feb 10, 2026

参考 nv 平台，在摩尔平台实现 paged attention prefill 和 paged attention decode

paged attention prefill python 测试：
image

paged attention decode python 测试：
image

@spike-zhu spike-zhu requested review from a team and wooway777 February 10, 2026 09:07
@spike-zhu spike-zhu self-assigned this Feb 10, 2026
@spike-zhu spike-zhu mentioned this pull request Feb 11, 2026
Closed
@wooway777 wooway777 merged commit 84201ad into demo131 Feb 11, 2026
10 checks passed
@wooway777 wooway777 deleted the issue/1001 branch February 11, 2026 07:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@wooway777 wooway777 wooway777 approved these changes

Assignees

@spike-zhu spike-zhu

Labels

准备好了 模块：算子

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@spike-zhu @wooway777