vllm/docs/deployment/integrations/kserve.md

# KServe

vLLM can be deployed with [KServe](https://github.com/kserve/kserve) on Kubernetes for highly scalable distributed model serving.

You can use vLLM with KServe's [Hugging Face serving runtime](https://kserve.github.io/website/docs/model-serving/generative-inference/overview) or via [`LLMInferenceService` that uses llm-d](https://kserve.github.io/website/docs/model-serving/generative-inference/llmisvc/llmisvc-overview).