CUDA error: misaligned address
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 9k
- Forks
- 1.5k
- Avg merge
- 2d 4h
- Merged PRs (30d)
- 3
Description
@mcarilli
Opening a new issue even though it is similar to #124
However we seem to see this error only since the upgrade to the new API.
here is more detail posted by a user https://github.com/OpenNMT/OpenNMT-py/issues/1475
but we encountered the exact same thing at times.
When running in FP32 it goes very fine, switching to AMP we reproduce the same error.
Just in case you have some ideas to debug it.
Contributor guide
No contributing guide indexed for this repository
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 reading the related issues #124 and #1475, then reproduce the CUDA misaligned-address error described here by comparing FP32 with AMP after the new API upgrade. There is no named file, test, or defined fix in the issue, so completion would require identifying the cause and agreeing on a resolution.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100