Skip to content
This repository was archived by the owner on Jan 15, 2026. It is now read-only.

CUDA OPSA VJP VJP#61

Open
rubber-duck-debug wants to merge 42 commits intomainfrom
cuda_vjpvjp_opsa
Open

CUDA OPSA VJP VJP#61
rubber-duck-debug wants to merge 42 commits intomainfrom
cuda_vjpvjp_opsa

Conversation

@rubber-duck-debug
Copy link
Collaborator

No description provided.

@rubber-duck-debug rubber-duck-debug changed the title WIP for OPSA VJP VJP WIP for CUDA OPSA VJP VJP May 2, 2024
@rubber-duck-debug rubber-duck-debug changed the title WIP for CUDA OPSA VJP VJP CUDA OPSA VJP VJP May 2, 2024
@rubber-duck-debug rubber-duck-debug changed the title CUDA OPSA VJP VJP WIP CUDA OPSA VJP VJP May 2, 2024
@rubber-duck-debug rubber-duck-debug added the WIP work in progress label May 2, 2024
@rubber-duck-debug rubber-duck-debug removed the WIP work in progress label May 3, 2024
@rubber-duck-debug rubber-duck-debug 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 subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants