TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Contributions:72 pushes, 23 branches in 1 year 1 month
InCube Core libraries for C#
Contributions:1 release, 118 commits, 23 pushes in 9 months
csharpfunctional-programingcsharp-corenullableoption-type