alt Hacker NewsI follow the llama.cpp runtime improvements and it’s also true for this project. They may rush a bit less but you also have to wait for a few days after a model release to get a working runtime with most features.
I follow the llama.cpp runtime improvements and it’s also true for this project. They may rush a bit less but you also have to wait for a few days after a model release to get a working runtime with most features.
Model authors are welcome to add support to llama.cpp before release like IBM did for granite 4 https://github.com/ggml-org/llama.cpp/pull/13550