NVIDIA / NVIDIA/cuda-python

[FEA]: Ability to provide an extra path for cuda-pathfinder to search with high priority

Open
#1,054 7 comments 1 reaction 1 assignee View on GitHub

@rwgk is already working on this.

Since Sep 30, 2025.

awaiting-response cuda.pathfinder feature
Dominant language
Cython
Stars
3.4k
Forks
329
Avg merge
1d 23h
Merged PRs (30d)
116

Description

Is this a duplicate?
Area

cuda.pathfinder

Is your feature request related to a problem? Please describe.

The cuda-pathfinder's search path prioritizes libraries from wheels. For example, libnvshmem_host.so comes from libnvidia-nvshmem-cuXX wheel. If I'm working from a development branch of nvshmem, I may need to manually copy libraries over the site-packages directory in order to get my custom libraries to be opened. LD_LIBRARY_PATH is much lower in the priority order (on purpose), so that won't work either.

Describe the solution you'd like

A few different ideas come to mind:

  • <LIBNAME_UPPER_CASE>_PATH_OVERRIDE so each library has an ability to be overridden independently
  • CUDA_PATHFINDER_TOP_PRIORITY_PATH which applies to all pathfinder searches
  • Adding a <library>_HOME environment variable, and prioritizing it above other search paths
Describe alternatives you've considered

I think I listed all 3 above. The current hacky WAR is to copy .so files around on the system.

Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.