+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Context / KV Cache (https://www.datasculpting.ai/inference/forumdisplay.php?fid=41)
+--- Thread: prefix caching on repeated workflows on 7900 XTX (/showthread.php?tid=679)
Pages:
1
2
Re: prefix caching on repeated workflows on 7900 XTX - cacheline - 10-11-2026
Quote:My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs. Once you know
I'd approach it in a boring order. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: prefix caching on repeated workflows on 7900 XTX - dockember - 10-12-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there.
Re: prefix caching on repeated workflows on 7900 XTX - cacheline - 10-12-2026
That matches what I was seeing. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: prefix caching on repeated workflows on 7900 XTX - marbleyard32 - 10-12-2026
subscribed, curious where this lands.
Re: prefix caching on repeated workflows on 7900 XTX - cacheline - 10-12-2026
Appreciate the detail. That matches what I saw on dual 3090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.