NVIDIA / NVIDIA/cuEquivariance
cuet.SegmentedPolynomial does not support fp16/bf16 for math_dtype?
Open
Nobody has claimed this yet.
feature request
- Dominant language
- Python
- Stars
- 433
- Forks
- 42
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
I was wondering if it could be possible to implement fp16/bf16. I am getting errors that only fp64 and fp32 are available.
Thank you very much.
Regards
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 at cuet.SegmentedPolynomial and inspect how math_dtype currently limits support to fp32 and fp64. Determine the expected behavior for fp16 and bf16, then verify that both dtypes work without the reported errors; the issue does not name a file or test to run.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100