{"id":"litserve","name":"LitServe","maker":"Lightning AI","url":"https://lightning.ai/docs/litserve","repo":"Lightning-AI/LitServe","package":"pypi:litserve","summary":"A Python framework for building custom model inference servers on FastAPI, with batching and GPU autoscaling.","details":"LitServe lets a developer define a server for any model, including agents and language models, with streaming and an optional OpenAI-compatible spec. It is under the Apache licence and runs anywhere Python does.","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/litserve","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true,"repository":{"at":"2026-11-16T02:35:24.378Z","archived":false,"licence":"Apache-2.0","language":"Python","last_change":"2026-11-01T21:03:30.000Z","latest_release":{"tag":"v0.2.19","published":"2026-09-09T17:10:09.000Z"}}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}