ZSE
Open-source LLM inference engine that cuts GPU memory use and starts models quickly. It offers an OpenAI-compatible API server, a CLI, a web dashboard and CPU fallback.
Open sourceCoding & Development
Visit website(opens in a new tab)
Open-source LLM inference engine that cuts GPU memory use and starts models quickly. It offers an OpenAI-compatible API server, a CLI, a web dashboard and CPU fallback.