where reranking mattered: what are you seeing?

[orbitgarden]

Thought I'd post a small recipe because a lot of threads ask similar things.

This isn't revolutionary, but the combination of llama.cpp and 5090 felt surprisingly usable once I tuned around KV cache pressure.

If someone wants the exact settings I can clean them up and post them.

[tinycontext]

Interesting, I hadn't tried that. The pattern around workstation thermals has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.

[torchsupply99]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.

[macropilot]

Thanks, that helps. I don't think your conclusion is far off.

[kernelghost]

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.

[labpath]

I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.

[deltastation]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching.

[modbench]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching.

I hit almost the same issue last night.

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

[tinycontext]

[quote]A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching

Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.

[tensorfield88]

Need a little more detail here. What model, what runtime, and roughly what context size?