{"id":"tensorrt-llm","name":"TensorRT-LLM","maker":"NVIDIA","url":"https://nvidia.github.io/TensorRT-LLM/","repo":"NVIDIA/TensorRT-LLM","package":"pypi:tensorrt-llm","summary":"A library from NVIDIA with a Python API for defining and running language models efficiently on NVIDIA GPUs.","details":"TensorRT-LLM provides optimised kernels, quantization, batching and a trtllm-serve command that offers an OpenAI-compatible server. It runs only on NVIDIA GPUs.","open_source":true,"hosted":false,"speaks":["openai-api"],"verified":"2026-11-15","category":"runtimes","category_name":"Local and self-hosted model runtimes","page":"https://modelmoot.com/tools/tensorrt-llm","reviewed":"2026-11-15","checked":{"at":"2026-11-15T16:10:15.342Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}