when a plain Python stack is enough

[cudacrate]

Posting this in case it saves someone else a little time.

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about reranking.

I'm especially interested in mistakes worth avoiding.

I care more about stability than squeezing the last possible tokens/sec out of it.

[mangohouse]

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. Not glamorous advice, but repeatable baselines save a lot of time.

[localcraft17]

I think the bottleneck is somewhere else. I get why that seems right, but on 7900 XTX the bottleneck felt elsewhere.

[sanevault]

Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

[deltapoint17]

Need a little more detail here. Are you testing this on GB200 or something else?

[vramghost]

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.

I'm happy to test one more variant if you want a second data point.

[kernelrunner]

Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency,

My first guess would be this: If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.