This repository was archived by the owner on Jul 4, 2025. It is now read-only.

Description
Goal
Currently, with GGUF model files we ship a model.yml file which contains extra parameters not generally available in GGUF files such as inference parameters and so on. Given that cortex also/will use vllm as a backend, consider removing model.yml file and use gguf-editor to set extra parameters in the GGUF itself.