Apple unified memory limits with vLLM

[visionyard23]

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

I don't think that's the whole story. I've seen people blame continuous batching when the real issue was much more mundane. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[dockridge]

Tried to reproduce it just now. On mini PC with llama.cpp, I saw basically the same behavior.

[mlxgarden]

What exact setup are you running? What model, what runtime, and roughly what context size?

[sanescope]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.