Jan Wessling
Jan Wessling
Hey, any update on when python 3.11 will be supported?
Could this be the reason why I am seeing very slow performance serving a tensorrt-llm model with the backend using the ensemble model compared to benchmarks for a similar model...
I am using the 24.11-trtllm-python-py3 image
I will add a new issue for it
here: https://github.com/triton-inference-server/tensorrtllm_backend/issues/667
any updates on this