NVIDIA / NVIDIA/TensorRT-LLM

[Question] tensorrt and tensorrtllm in the same image

Open
#11,041 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Investigating question
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

How would you like to use TensorRT-LLM

hi,

im currently using nvcr.io/nvidia/tritonserver:25.09-trtllm-python-py3.
is there a way to use tensorrt and tensorrt-llm using the same image? i have a gemma3 and modernbert model i want to use on a single gpu using the same docker image. can i build a customer image for tritonserver - who would know that here?

Before submitting a new issue...
  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

cc @karljang @MrGeva @QiJune

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the nvcr.io/nvidia/tritonserver:25.09-trtllm-python-py3 image and review the linked TensorRT-LLM documentation and examples. Determine whether TensorRT and TensorRT-LLM can coexist for the Gemma3 and ModernBERT models on one GPU, and document whether a custom TritonServer image is supported and how it should be built.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, python
Domain
backend, devops
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.