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
Hi Xiaotao,
Thanks for this wonderful tool. I am currently running EagleC on a machine with 4 Quadro RTX 5000 (I hope this would be faster than running on cpu only...) But with one of the gpu largely occupied by another job. However when initiating EagleC run it encounter an error: could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR
I assume this could be caused by the low memory in that occupied gpu. I there a way like specifying threads, in specifying number (or which) gpu to use?
Best,
Yang
The text was updated successfully, but these errors were encountered:
Hi Yang, sorry for the delayed response. Just wanted to let you know that while EagleC used GPU for training, it does not currently support GPU for prediction.
Hi Xiaotao,
Thanks for this wonderful tool. I am currently running EagleC on a machine with 4 Quadro RTX 5000 (I hope this would be faster than running on cpu only...) But with one of the gpu largely occupied by another job. However when initiating EagleC run it encounter an error:
could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR
I assume this could be caused by the low memory in that occupied gpu. I there a way like specifying threads, in specifying number (or which) gpu to use?
Best,
Yang
The text was updated successfully, but these errors were encountered: