human evals on small teams

[fusedtinker]

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

This isn't revolutionary, but the combination of SGLang and mini PC felt surprisingly usable once I tuned around tokens/sec.

Feel free to tear it apart if you see something dumb.

If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.

[signalcraft14]

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?

[thetashed24]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. Once you know the plain path works, then add the faster path back in piece by piece.

[rasterhall]

Thanks, that helps. I ended up in about the same place using llama.cpp. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[kernelhouse70]

Can you fill in a bit more context? Are you testing this on 5090 or something else?

[cachelab]

Can you fill in a bit more context? Are you testing this on 5090 or something else?

I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly.