google-deepmind / google-deepmind/tapnet
TAPIR performance degradation with cudnn9
Open
- Dominant language
- Jupyter Notebook
- Stars
- 2k
- Forks
- 192
- PR merge metrics
- No merged PRs in 30d
Description
Internally running with cudnn9 results in poor TAPIR performance. It's unclear if anyone external has encountered the same issue. Our teams have traced the issue to a broken cudnn9 convolution kernel. This is being tracked in the following bug at nvidia:
https://partners.nvidia.com/bug/viewbug/4705291
Contributor guide
Assessment
This issue has not been assessed yet.