Avoid using non-polymorphic CUDA graph APIs internally
Open
Nobody has claimed this yet.
breaking
cuda.core
enhancement
- Dominant language
- Cython
- Stars
- 3.4k
- Forks
- 329
- Avg merge
- 1d 23h
- Merged PRs (30d)
- 116
Description
The non-polymorphic graph APIs (that is, those calling out the node names/types) are considered deprecated and will be removed in a future CUDA release. We should have everything we need to migrate to the polymorphic versions such as cuGraphAddKernelNode, cuGraphExecKernelNodeSetParam, ...
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating internal uses of the non-polymorphic CUDA graph APIs named in the issue, including the kernel-node operations. Compare each use with its polymorphic counterpart and verify that internal calls no longer use the deprecated forms; the issue does not name specific files or tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api
- Issue type
- Refactor
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 52/100