📄️ Overview
RayLLM APIs are in Beta.
📄️ Bring any Hugging Face model
Bring any vLLM compatible model with any prompt format.
📄️ Playground
Experiment with deployed LLM services on the web.
📄️ RayLLM deployment options
Explains all the deployment options with RayLLM
📄️ JSON mode
JSON Mode with RayLLM
📄️ Multi-LoRA deployment
Efficiently run multiple LoRA models with a single deployment.
📄️ Serving vision language models
Vision Language Models with RayLLM
📄️ Migrate from OpenAI to open models
Migrate from OpenAI to self-deployed OpenAI compatible Server