TensorRT LLM is not working.

## What this teaches

How to tensorRT LLM is not working..

## The problem

Issue modal-labs/modal-client#1318 (closed, 6 comments): ### Steps to reproduce Here are the steps to reproduce the TensorRT 1. I am using this custom docker image named [anindyadeep/tensorrt_llm:release](https://hub.docker.com/layers/anindyadeep/tensorrt_llm/release/images/sha256-42aaa553a695223a466ad8ce74b3cbb79cdfe5bb8f54090fc445412fbfbab796?context=repo) that I build through TensorRT-LLM. 2.

## What worked (verified answer)

TensorRT-LLM custom image failing on Modal: pass the gpu argument to run_function (and pip_install), not to from_image(). In your code: .run_function(hello_world, secrets=[Secret.from_name("your-huggingface-secret")], gpu=GPU_CONFIG). The gpu kwarg belongs on the function call that executes, not on the image builder.

## Source

gh:modal-labs/modal-client#1318 - https://github.com/modal-labs/modal-client/issues/1318