tensorrt-lean-cu12 10.4.0

A high performance deep learning inference library

NVIDIA TensorRT is an SDK that facilitates high-performance machine learning inference. It is designed to work in a complementary fashion with training frameworks such as TensorFlow, PyTorch, and MXNet. It focuses specifically on running an already-trained network quickly and efficiently on NVIDIA hardware.

IMPORTANT: This is a special release of TensorRT designed to work only with TensorRT-LLM. Please refrain from upgrading to this version if you are not using TensorRT-LLM.

To install, please execute the following:

pip install tensorrt --extra-index-url https://pypi.nvidia.com

Or add the index URL to the (space-separated) PIP_EXTRA_INDEX_URL environment variable:

export PIP_EXTRA_INDEX_URL='https://pypi.nvidia.com'
pip install tensorrt

When the extra index url does not contain https://pypi.nvidia.com, a nested pip install will run with the proper extra index url hard-coded.