Iman Tabrizian

@cclauss Thanks for fixing all these typos! Could you please sign the [CLA ](https://github.com/triton-inference-server/server/blob/main/Triton-CCLA-v1.pdf) and send it to [[email protected]](mailto:[email protected])? https://github.com/triton-inference-server/server/blob/main/CONTRIBUTING.md#contributor-license-agreement-cla

Hi @Michael-Jing, sorry about the delay. Can you please share the structure of your model repository? Are you copying `triton_python_backend_utils` in your model directory? If yes, that is why you...

@ikhyun5538 Can you clarify more on the feature request? You can create a larger batch by providing more elements in the first batch of your model. For example, if the...

Sorry for the delay in responding to this thread. I'm still not completely clear on the feature request. Why the additional metadata that you want to send cannot be a...

Closing due to in-activity.

It is the first time but I think it is a reasonable ask. Please file a ticket for it. Thanks.

Are you running the client in a different container? If yes, you need to add `--ipc host` flag to both of the containers.

Hi @jennyHsiao, I think the CUDA library used in the `triton_python_backend_stub` can be different from the CUDA library used in the TF Python package. Are you installing CUDA using `conda...

@Jackiexiao This sounds like a reasonable request to me. I think we should deliver the flag to the client indicating whether this is the last response or not. Right now,...

> We have many large inputs on GPU, and it seems they are being copied before being sent downstream to the other backend. Can you fully describe your inference pipeline?...