Ray Serve LLM
Build fast, scalable, and cost-effective LLM services.
An LLM-serving framework within Ray Serve for deploying and scaling large-language-model inference workloads.
Recent stories
0 linked stories
No linked stories yet.
Build fast, scalable, and cost-effective LLM services.
An LLM-serving framework within Ray Serve for deploying and scaling large-language-model inference workloads.