luohao123 opened a new issue #9086:
URL: https://github.com/apache/tvm/issues/9086


   Does tvmc supports call tensorrt target compile for model generate on cuda? 
   
   I currently tuning a model, the different hardware performance:
   
   CPU: 1s
   GPU (cuda): 200ms
   TensorRT: unknown
   
   Pytorch: 20ms
   
   How to make GPU speed comparable with pytorch? No matter than using cuda or 
TensorrT


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


Reply via email to