+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Prompting & Context Engineering (https://www.datasculpting.ai/inference/forumdisplay.php?fid=15)
+--- Forum: Prompts / System Prompts (https://www.datasculpting.ai/inference/forumdisplay.php?fid=62)
+--- Thread: few-shot when you actually need it (/showthread.php?tid=1435)
Pages:
1
2
few-shot when you actually need it - thetafield - 10-18-2026
Spent some time on this today and wanted to compare notes.
Two paths both seem viable, but they break down differently once long context becomes important.
Trying to avoid rebuilding the whole thing twice.
Re: few-shot when you actually need it - quiettoken - 10-18-2026
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: few-shot when you actually need it - mlxgarden - 10-18-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at HBM constraints.
Re: few-shot when you actually need it - quantyard - 10-18-2026
Thanks, that helps. I ended up in about the same place using SGLang. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: few-shot when you actually need it - mintstation99 - 10-18-2026
Quote:Thanks, that helps. I ended up in about the same place using SGLang. Worth rechecking your defaults though, because one bad assumption can make the re
I think the bottleneck is somewhere else. I've seen people blame embeddings when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: few-shot when you actually need it - thetaarch43 - 10-18-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs.
Re: few-shot when you actually need it - deltastation - 10-18-2026
I'd start with the simpler stack.
Re: few-shot when you actually need it - mlxgarden - 10-18-2026
Interesting, I hadn't tried that. I don't think your conclusion is far off.
Re: few-shot when you actually need it - northgarden37 - 10-19-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
Re: few-shot when you actually need it - thetafield - 10-19-2026
What exact setup are you running? Is this local-only or are you routing anything externally?