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

Support JIT compilation for CUDA driver & bindings 11.x #188

Merged
merged 7 commits into from
Oct 28, 2024

Conversation

leofang
Copy link
Member

@leofang leofang commented Oct 25, 2024

Close #187.

This PR fixes two issues:

  1. launch does not support the old cuLaunchKernel API
  2. CUmodule/CULibrary handling. Below is what's implemented in this PR:
cuda-python version driver version which to use reason
11.x 11.x CUModule only old symbols/APIs exist
11.x 12.x CUModule binding does not expose the new symbols/APIs from the driver
12.x 11.x CUModule driver does not support the new symbols/APIs
12.x 12.x CULibrary both old/new can be used, prefer the new ones for contextless support

@leofang leofang added enhancement Any code-related improvements P0 High priority - Must do! cuda.core Everything related to the cuda.core module labels Oct 25, 2024
@leofang leofang added this to the cuda.core beta 1 milestone Oct 25, 2024
@leofang leofang self-assigned this Oct 25, 2024
Copy link

copy-pr-bot bot commented Oct 25, 2024

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@leofang leofang marked this pull request as ready for review October 26, 2024 01:59
Copy link
Collaborator

@vzhurba01 vzhurba01 left a comment

Choose a reason for hiding this comment

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

LGTM, thank you for the explanations!

@leofang
Copy link
Member Author

leofang commented Oct 28, 2024

Merging, thanks for careful review, Vlad!

@leofang leofang merged commit e426810 into NVIDIA:main Oct 28, 2024
@leofang leofang deleted the cuda_core_11 branch October 28, 2024 22:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cuda.core Everything related to the cuda.core module enhancement Any code-related improvements P0 High priority - Must do!
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Implement launch() to support CUDA 11.x driver
2 participants