Iman Tabrizian

>(parameter sweep) I could not gain larger throughputs than the one with my previous parameters. I guess there's no room for performance improvement with the parameter sweep. Can you share...

Q1: There is a known issue with Model Analyzer reporting incorrect GPU usage numbers. It is being actively worked on and hopefully will be addressed soon. Apart from that, you...

Hi @badskeet, the shared memory implementation is completely transparent to the Python model (i.e. you won't interact directly with shared memory). You can create a tensor and store it as...

@Phelan164 Sorry for delay in responding to this thread. Importing `Tensor` from `triton_python_backend_utils` is not supported before `initialize` function is called. We can fix this issue in Python models. I'll...

> Not sure if the issue is only in building the environment, I've tried packaging the environment in WSL on a windows laptop and then starting the server on my...

Closing due to in-activity.

@GuanLuo Do you happen to know why this might happen?

I'll try to see if I can find any good candidates for unit testing. I think an end-to-end test is better suited for this feature. Unit testing this feature would...

Hi @gandharv-kapoor I think your best bet would be to prepare your own base container that has all the dependencies that the `tritonserver` min image has and use 18.04 ubuntu...

>Cant I use an existing docker file with dependencies listed for triton? The problem is that the Dockerfile for the `min` container is not published. For building Triton on Ubuntu...