prefix caching on repeated workflows

[cacheline]

That matches what I was seeing. I ended up in about the same place using MLX. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[marbletrack]

Thanks, that helps. The pattern around tokens/sec has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

If you post your exact settings, people here can probably narrow it down pretty fast.

[cacheline]

My first guess would be this: If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[southspark]

Good point. I don't think your conclusion is far off.

[macropilot]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tokens/sec.