The project dockerises the deployment of oobabooga/text-generation-webuiand its variants. It provides a default configuration (corresponding to a vanilla deployment of the application plus pre-installed PanQiWei/AutoGPTQ library) as well as pre-configured support for other set-ups (e.g., latest llama-cpp-python with GPU offloading, the more recent triton and cuda branches of GPTQ).