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

Fetch runtime version with cuda-python instead of numba. #948

Open
bdice opened this issue Jan 19, 2022 · 4 comments · May be fixed by #1675
Open

Fetch runtime version with cuda-python instead of numba. #948

bdice opened this issue Jan 19, 2022 · 4 comments · May be fixed by #1675
Assignees
@Matt711
Labels
good first issue Good for newcomers Python Related to RMM Python API

Comments

@bdice
Copy link
Contributor

bdice commented Jan 19, 2022

PR #946 introduces a workaround for an issue in cuda-python that fetches a hardcoded CUDA runtime version. NVIDIA/cuda-python#16

Once that upstream issue is resolved, we should update the implementation in RMM to use cuda.cudart.cudaRuntimeGetVersion() instead of numba.cuda.runtime.get_version().

Originally posted by @jakirkham in #946 (comment)
@bdice bdice mentioned this issue Jan 19, 2022
Merged
@galipremsagar galipremsagar mentioned this issue Jan 19, 2022
Closed
@github-actions
Copy link

This issue has been labeled inactive-30d due to no recent activity in the past 30 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed. This issue will be labeled inactive-90d if there is no activity in the next 60 days.

@github-actions
Copy link

This issue has been labeled inactive-90d due to no recent activity in the past 90 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed.

@wence-
Copy link
Contributor

wence- commented Jul 20, 2023

Just to note, this will likely be possible with cuda 12.3, so we should revisit then.

@harrism harrism added good first issue Good for newcomers Python Related to RMM Python API and removed inactive-90d inactive-30d labels Jan 18, 2024
@bdice
Copy link
Contributor Author

bdice commented Jan 18, 2024 •
edited
Loading

An API for getting the local CUDA runtime version was added in cuda-python 12.3, as cudart.getLocalRuntimeVersion().

12.3.0 release notes: https://nvidia.github.io/cuda-python/release/12.3.0-notes.html

It was also backported to cuda-python 11.8.3: https://nvidia.github.io/cuda-python/release/11.8.3-notes.html

To resolve this issue, we should switch to using that API and update the minimum version requirements. However, we may not be able to update to cuda-python 12.3 yet. I'm not sure, it depends on how the conda-forge cuda-version and CUDA Toolkit compatibility works with cuda-python packages. I don't think it was backported to cuda-python 12.2.1.

@Matt711 Matt711 linked a pull request Sep 9, 2024 that will close this issue
Open
3 tasks
@Matt711 Matt711 self-assigned this Sep 12, 2024
@Matt711 Matt711 moved this to In Progress in RMM Project Board Sep 12, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Matt711 Matt711

Labels
good first issue Good for newcomers Python Related to RMM Python API
Projects
RMM Project Board
Status: In Progress
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

[Improvement] Fetch runtime version with cuda-python instead of numba Matt711/rmm
4 participants
@harrism @wence- @bdice @Matt711