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.
NVIDIA Corporation
Repositórios que pertencem a NVIDIA Corporation, uma organização no GitHub.
3 ferramentas
cuDF - GPU DataFrame Library
- Linguagem
- C++
- Licença
- Apache-2.0
- Estrelas
- 9.8k
- Última release
- v26.08.01
- Último push
- 2026-10-06
the LLM vulnerability scanner
- Linguagem
- Python
- Licença
- Apache-2.0
- Estrelas
- 9.5k
- Última release
- v0.17.0
- Último push
- 2026-10-02