TRT-LLM fails on GH200 node

[ttim]

System Info

• GH200 x1, lambdalabs
• TRT LLM 0.15.0
• nvcr.io/nvidia/pytorch:24.10-py3 base image

pip install succeeds, but running code fails with

  File "/usr/local/lib/python3.10/dist-packages/tensorrt_llm/__init__.py", line 32, in <module>
    import tensorrt_llm.functional as functional
  File "/usr/local/lib/python3.10/dist-packages/tensorrt_llm/functional.py", line 25, in <module>
    import tensorrt as trt
ModuleNotFoundError: No module named 'tensorrt'

Who can help?

@byshiue

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

1. Use docker image nvcr.io/nvidia/pytorch:24.10-py3
2. Install trt llm 0.15.0 version
3. Try to run

Expected behavior

• Works

actual behavior

• Fails

additional notes

None

[nv-guomingz]

@Shixiaowei02 could u please answer this question?