Model serving
TensorRT LLM
Optimize and run language-model inference on NVIDIA GPUs.
Where it fits
What you can use it for
Teams tuning serving performance for NVIDIA hardware.
Serve models with the performance and control your workload needs.
Before you adopt
What to check for your team
Check whether your deployment includes the LTX-2 code and whether its revenue or competition restrictions apply. The Apache-2.0 core label does not cover that directory. Also verify GPU, driver and model support.
Get help evaluating the fitLicence and scope
Apache-2.0 core
The core is Apache-2.0. Code in tensorrt_llm/_torch/visual_gen/models/ltx2/ uses the LTX-2 Community License: entities with annual revenue of at least US$10 million need a paid commercial license, and competing products or services require a separate commercial license. Other bundled code and runtime dependencies have separate terms.
Read the upstream licenceSupport the work
Go directly to the maintainers
Use the project's contribution guidance to report issues, help with documentation or contribute code. Follow any published funding links if you want to support the maintainers financially.
Find contribution guidanceKeep exploring
