Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Run on the correct CUDA stream#175

Open
xrq-phys wants to merge 1 commit into
thu-ml:mainfrom
xrq-phys:fix/cuda_stream
Open

Run on the correct CUDA stream#175
xrq-phys wants to merge 1 commit into
thu-ml:mainfrom
xrq-phys:fix/cuda_stream

Conversation

@xrq-phys
Copy link
Copy Markdown

This patch tries to ensure when one runs sageattn under:

with torch.cuda.stream(stream):
    sageattn(q, k, v)

all kernels would be enqueued onto the correct CUDA stream.

@walker-ai
Copy link
Copy Markdown

Hi, I'm currently working on support CUDA graph of SA, but I've encountered some output errors. I want to know if this PR is related to me. Maybe this stream issue could cause some correctness errors?

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants