{"id":"triton-inference-server","name":"Triton Inference Server","maker":"NVIDIA","url":"https://developer.nvidia.com/triton-inference-server","repo":"triton-inference-server/server","summary":"An inference server that serves models from several frameworks over HTTP and gRPC, with batching and ensembles.","details":"Triton runs TensorRT, PyTorch, ONNX and other backends, including a TensorRT-LLM and a vLLM backend, and includes an OpenAI-compatible frontend. It is delivered as a container and runs on GPUs and CPUs.","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/triton-inference-server","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."}