- Repository
- https://github.com/NVIDIA/TensorRT-LLM
- Homepage
- https://nvidia.github.io/TensorRT-LLM
- Owner
- NVIDIA (Organization)
- Stars
- 14,849
- Forks
- 2,832
- Open issues
- 1,707
- Language
- Python
- License
- Other
- Created
- 2023-08-16
- Last push
- 2026-10-18
- Topics
- blackwell, cuda, llm-serving, moe, pytorch
- Snapshot
- 2026-10-18
GitHub · #548
NVIDIA/TensorRT-LLM
NVIDIA/TensorRT-LLM is #548 in this GitHub directory, with 14,849 stars. 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…