+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Other Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=39)
+--- Thread: throughput per watt reality check (/showthread.php?tid=1058)
Pages:
1
2
Re: throughput per watt reality check - cachelab - 10-18-2026
What worked for me was pretty simple. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: throughput per watt reality check - batchsize - 10-18-2026
Interesting, I hadn't tried that. That matches what I saw on 7900 XTX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: throughput per watt reality check - plainscope50 - 10-19-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at reranking. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: throughput per watt reality check - vectorshed43 - 10-19-2026
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
Re: throughput per watt reality check - rocmpath - 10-19-2026
I don't think that's the whole story. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: throughput per watt reality check - mlxgarden - 10-19-2026
A couple things I'd check first. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives.