+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Distillation (https://www.datasculpting.ai/inference/forumdisplay.php?fid=55)
+--- Thread: RAG chunking that actually helped on Threadripper box (/showthread.php?tid=999)
Pages:
1
2
Re: RAG chunking that actually helped on Threadripper box - tensorriver - 10-15-2026
I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Re: RAG chunking that actually helped on Threadripper box - mangopath4 - 10-15-2026
That matches what I was seeing. 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: RAG chunking that actually helped on Threadripper box - byteyard - 10-15-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there.
Re: RAG chunking that actually helped on Threadripper box - phaseport36 - 10-17-2026
A couple questions before I guess too hard. What model, what runtime, and roughly what context size?
Re: RAG chunking that actually helped on Threadripper box - thetaplane - 10-17-2026
Not sure I agree there. 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. The logs were somehow calmer than I was.
Re: RAG chunking that actually helped on Threadripper box - orbitline - 10-18-2026
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.