+- 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: setup advice (/showthread.php?tid=732)
Pages:
1
2
synthetic data for support bots: setup advice - cacheworks - 10-05-2026
Did a bit of testing and thought I'd post the result here.
Short version: vLLM behaved well for me, but only after I stopped ignoring NVFP4.
Nothing scientific here, just practical notes from a real setup.
Re: synthetic data for support bots: setup advice - batchember - 10-05-2026
same here on my side.
Re: synthetic data for support bots: setup advice - routecraft - 10-08-2026
Quote:same here on my side.
Maybe, but I had the opposite result. I get why that seems right, but on A6000 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.
Re: synthetic data for support bots: setup advice - routeline23 - 10-08-2026
Good point. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: synthetic data for support bots: setup advice - quantsupply - 10-09-2026
Appreciate the detail. That matches what I saw on Threadripper box.
Re: synthetic data for support bots: setup advice - quantghost - 10-09-2026
Quote:Appreciate the detail. That matches what I saw on Threadripper box.
Did a small comparison this afternoon. On 7900 XTX with LM Studio, I saw basically the same behavior. I expected the model choice to matter more than it did.
Re: synthetic data for support bots: setup advice - rocmplane - 10-09-2026
Need a little more detail here. Are you testing this on 4090 or something else?
Re: synthetic data for support bots: setup advice - mellowwire98 - 10-10-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there.
Re: synthetic data for support bots: setup advice - rocmplane - 10-10-2026
My first guess would be this: 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.
Re: synthetic data for support bots: setup advice - routecraft - 10-11-2026
subscribed, curious where this lands.