xkiwilabs
-
llm-inference-hub
A reproducible LLM inference stack built on vLLM + LiteLLM, designed for multi-GPU Ubuntu workstations. Serves multiple models simultaneously over a single OpenAI-compatible API.
A reproducible LLM inference stack built on vLLM + LiteLLM, designed for multi-GPU Ubuntu workstations. Serves multiple models simultaneously over a single OpenAI-compatible API.