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]: support seqlen_q large than 1 for PagedAttention with FP8KV #181

Open
sijiac opened this issue Mar 6, 2025 · 0 comments
Open

[Feature]: support seqlen_q large than 1 for PagedAttention with FP8KV #181

sijiac opened this issue Mar 6, 2025 · 0 comments

Comments

@sijiac
Copy link
Contributor

sijiac commented Mar 6, 2025

Suggestion Description

The current pa_fwd_asm kernel only supports seqlen_q = 1. However, speculative decoding scenarios require handling seqlen_q values of 2 or 4, depending on the configuration. We need to add support for these cases

Thanks!!

cc @carlushuang

Operating System

No response

GPU

MI300

ROCm Component

No response
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
@sijiac