| 1 | # KServe |
| 2 | |
| 3 | vLLM can be deployed with [KServe](https://github.com/kserve/kserve) on Kubernetes for highly scalable distributed model serving. |
| 4 | |
| 5 | 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). |