masahi commented on issue #9939:
URL: https://github.com/apache/tvm/issues/9939#issuecomment-1013799936


   > Is this outdated?
   
   No, this is specific to the model used in that tutorial (MaskRCNN) and not 
about VM per se. 
   
   
   
   > 2\. Compiling with VM is going to bake it into the model and running it 
with C++ won't require me to use a VM
   
   You still need the VM runtime to run the model in your C++ app. The linked 
example 
https://github.com/apache/tvm/blob/e7024fb39ea27494fa5618102dae42e7e5551986/src/contrib/torch/pt_call_tvm/tvm_class.cc#L143
 shows how to use VM runtime C++ API.
   
   > Also, your examples all point to PyTorch, is that because they are good 
examples and I can do everything they do with ONNX as well, or should I use 
PyTorch to achieve the functionality I need?
   
   It doesn't matter, after a model is imported via PyTorch or ONNX, the 
compilation and deployment flow are exactly the same. It's just that I'm more 
familiar with PyTorch.


-- 
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