feat(gguf): run experts whose gate_up and down mix float and quantized types - #702

feat(gguf): run experts whose gate_up and down mix float and quantized types#702

jason-fxz merged 3 commits into

mainFlashML-org/FreeToken:mainfrom

feat/gguf-mixed-expertsFlashML-org/FreeToken:feat/gguf-mixed-expertsCopy head branch name to clipboard