TensorRT-LLM license, foundation and stars
Model serving and local AI · Custom or mixed (see the LICENSE file) (source-available) · backed by Nvidia · 14,713 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 execution in a performant way.
License history
LICENSE fileCustom or mixed (see the LICENSE file) No license change recorded since the repository was created in 2023.
Latest release
No GitHub releases published; the project releases elsewhere (tags or its own site).
More in model serving and local ai
| Project | Stars | |||
|---|---|---|---|---|
 OllamaOllamaMIT | MIT | 182k | +588 | v0.34.4Sep 23, 2026 |
 llama.cppMIT | MIT | 129k | +819 | v0.5.0Sep 23, 2026 |
 vLLMPyTorch FoundationApache 2.0 | Apache 2.0 | 92.7k | +548 | v0.30.0Sep 22, 2026 |
 gpt4allMIT | MIT | 77.4k | - | - |
| whisper.cppMIT | MIT | 53.9k | - | - |
 LocalAIMIT | MIT | 49.3k | - | - |
 JanMenlo ResearchApache 2.0 | Apache 2.0changed May 2025 | 44.6k | - | - |
 BitNetMicrosoftMIT | MIT | 40.3k | - | - |
About and history
- Repository
- NVIDIA/TensorRT-LLM · created Aug 16, 2023
- Website
- nvidia.github.io/TensorRT-LLM
- Language
- Python
- Foundation
- None; run by Nvidia
- Company
- Nvidia · on Companies · on Acquisitions · on awards · on blogs · on certifications · on Quarterly · on Mainstage · on Leaders · on Arena · on marketplaces · on papers · on Allied · on Paydays · on predictions · on quotes · on Releases · on TechConf · on training · on Hotlist
- GitHub detects
- NOASSERTION (a custom or multi-license file; the license above is read from the file itself)
- Stars per week
- From the second weekly snapshot
Weekly snapshots
| Week of | Stars | |
|---|---|---|
| Sep 21, 2026 | 14,713 |
Changes
| What changed | |
|---|---|
| Sep 25, 2026 | TrackedAdded: NVIDIA/TensorRT-LLM |