{"id":"llm-d","name":"llm-d","maker":"llm-d project","url":"https://llm-d.ai","repo":"llm-d/llm-d","summary":"A Kubernetes-native framework for distributed model serving, built on vLLM, with cache-aware routing.","details":"llm-d provides deployment recipes, an inference gateway and prefill and decode separation for serving large models on clusters. It is an open source project under the Apache licence supported by several companies.","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/llm-d","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}