The Windows release of TensorRT-LLM is currently in beta. We recommend using the `rel` branch for the most stable experience.
TensorRT-LLM is supported on bare-metal Windows for single-GPU inference. The release supports GeForce 40-series GPUs.
The release wheel for Windows can be installed with pip. Alternatively, you can build TensorRT-LLM for Windows from the source. Building from the source is an advanced option and is not necessary for building or running LLM engines. It is, however, required if you plan to use the C++ runtime directly or run C++ benchmarks.
To get started with TensorRT-LLM on Windows, visit our documentation: