You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The current implementation strategy for the driver-wrapper branch assumes we can obtain the CUDA driver handle for kernels - but that's only true since CUDA 11. We should support earlier versions - preferably via conditional complication, so as not to keep invalid code paths with newer CUDA versions.
The text was updated successfully, but these errors were encountered:
The current implementation strategy for the driver-wrapper branch assumes we can obtain the CUDA driver handle for kernels - but that's only true since CUDA 11. We should support earlier versions - preferably via conditional complication, so as not to keep invalid code paths with newer CUDA versions.
The text was updated successfully, but these errors were encountered: