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
Repositories von NVIDIA Corporation, einer Organisation auf GitHub.
3 Tools
cuDF - GPU DataFrame Library
- Sprache
- C++
- Lizenz
- Apache-2.0
- Sterne
- 9.8k
- Neuestes Release
- v26.08.01
- Letzter Push
- 2026-10-06
the LLM vulnerability scanner
- Sprache
- Python
- Lizenz
- Apache-2.0
- Sterne
- 9.5k
- Neuestes Release
- v0.17.0
- Letzter Push
- 2026-10-02