MAnasTahir

Results 4 comments of


                                            MAnasTahir

Tritonbackend multiple instances of the same model run sequentially instead of in parallel on the same device with asyncrhonous requests.

I am having same issue, but with models running on CPU. Instead of running in parallel it seems that models excute in sequence.

Access blocked

same error

[Python Backend] Send PbTensor to cpu for calling as_numpy() or add a function as_cupy()

Pytorch is not available with Pyton backend.

[Python Backend] Send PbTensor to cpu for calling as_numpy() or add a function as_cupy()

@tanmayv25 For deployments where we don't have direct access to containers, anyway to add it to container start command ?