One reason is that the llama.cpp team (GGML) has strict requirements that a human must understand the code they are contributing. If a project is fully vibe coded they can’t contribute. So a lot of projects where an AI went and coded a bunch of custom kernels to increase speed are left to their own devices.

I think this is a fine behavior. We can have upstream purists that are strict gatekeepers but don’t get in the way of downstream forks. Debian has some this in the Linux landscape for a long time, and it has enabled Ubuntu, Mint, etc. to flourish without compromising themselves.

The "mainstream" inference engines are notoriously slow to integrate this stuff, to an extent understandably given the complexity of ensuring numerical accuracy alongside supporting a wide array of systems and models. Part of it is that not everyone is willing to bring what they develop into a pull request because they vibe coded it and don't care to deal with whatever quality requirements the more well known inference engines have.