- Add validation rule to ensure is set to fastertransformer or python-backend
- Add warning if model is unavailable, likely the user has not set correctly
Signed-off-by: Parth Thakkar <thakkarparth007@gmail.com>
* Basic action that runs pytest
* fix indentation
* debugging actions :(
* pull the images in a separate step so it doesn't take so long to build
* Split out the container build
* Another try, fixing missing env vars
I'd been using dlpack for copying triton tensors to torch tensors,
which I did because it was advertised to perform zero copy transfers.
Turns out that only worked on my laptop, and didn't work on other machines.
IDK why. But for now, I'm just copying the tensors as triton<->numpy<->torch.
That works on the VM on which earlier code was segfaulting
Signed-off-by: Parth <thakkarparth007@gmail.com>
