cdoersch

Results 2 issues of cdoersch

A few people have emailed me about this now... When the code starts running, you may see something like this: ``` aggregate_covariance: 0+0/1500 working workers: 0 idle. aggregate_covariance: 0+0/1500 working...

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...