NVIDIA/TensorRT-LLM

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

语言：Python · GitHub 星标：15,024 · Fork：2,914

话题：blackwell · cuda · llm-serving · moe · pytorch

在 GitHub 上查看原仓库