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.

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

CUDA OPSA VJP VJP #61

Open
wants to merge 42 commits into
base: main
Choose a base branch
from
Open

CUDA OPSA VJP VJP #61

wants to merge 42 commits into from

Conversation

nickjbrowning
Copy link
Collaborator

No description provided.

@nickjbrowning nickjbrowning changed the title WIP for OPSA VJP VJP WIP for CUDA OPSA VJP VJP May 2, 2024
@nickjbrowning nickjbrowning changed the title WIP for CUDA OPSA VJP VJP CUDA OPSA VJP VJP May 2, 2024
@nickjbrowning nickjbrowning changed the title CUDA OPSA VJP VJP WIP CUDA OPSA VJP VJP May 2, 2024
@nickjbrowning nickjbrowning added the WIP work in progress label May 2, 2024
@nickjbrowning nickjbrowning removed the WIP work in progress label May 3, 2024
@nickjbrowning nickjbrowning changed the title WIP CUDA OPSA VJP VJP CUDA OPSA VJP VJP May 3, 2024
Copy link
Collaborator

@frostedoyster frostedoyster left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The code looks good and the gradgradcheck from Pytorch passes. However, I tried the CuPy tests and they segfaulted. This is probably due to the fact our CuPy interface doesn't feed CUDA streams to the C functions (#60)

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