+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Routers (https://www.datasculpting.ai/inference/forumdisplay.php?fid=45)
+--- Thread: synthetic data for support bots: anyone testing this? (/showthread.php?tid=893)
Pages:
1
2
synthetic data for support bots: anyone testing this? - routeline23 - 10-08-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Llama, llama.cpp, B200, with a lot of attention on tokens/sec.
If someone wants the exact settings I can clean them up and post them.
Re: synthetic data for support bots: anyone testing this? - promptpoint - 10-09-2026
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Re: synthetic data for support bots: anyone testing this? - phaseport36 - 10-09-2026
I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: synthetic data for support bots: anyone testing this? - deepseeked - 10-11-2026
What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: synthetic data for support bots: anyone testing this? - plainworks - 10-11-2026
I'd approach it in a boring order. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: synthetic data for support bots: anyone testing this? - phaseport36 - 10-13-2026
Quote:I'd approach it in a boring order. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.
worth checking the driver first.
Re: synthetic data for support bots: anyone testing this? - audioforge - 10-14-2026
worth checking the driver first.
Re: synthetic data for support bots: anyone testing this? - quantsupply - 10-15-2026
Quote:worth checking the driver first.
That matches what I was seeing. That matches what I saw on M3 Max.
Re: synthetic data for support bots: anyone testing this? - forgemixer - 10-15-2026
Appreciate the detail. I ended up in about the same place using PyTorch. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: synthetic data for support bots: anyone testing this? - plainline - 10-15-2026
Quote:Appreciate the detail. I ended up in about the same place using PyTorch. The biggest change for me was simplifying the stack instead of adding one mor
I don't think that's the whole story. I've seen people blame consumer GPUs when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.