+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Hardware (https://www.datasculpting.ai/inference/forumdisplay.php?fid=4)
+--- Forum: Systems & Builds (https://www.datasculpting.ai/inference/forumdisplay.php?fid=29)
+--- Thread: Threadripper build for inference (/showthread.php?tid=760)
Pages:
1
2
Re: Threadripper build for inference - sanevault - 10-10-2026
Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Worth testing the simpler explanation before adopting the more interesting one.
Re: Threadripper build for inference - promptfield - 10-12-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. Not glamorous advice, but repeatable baselines save a lot of time.
Re: Threadripper build for inference - edgequill - 10-12-2026
that fixed it for me too.
Re: Threadripper build for inference - plainscope50 - 10-12-2026
What worked for me was pretty simple. 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.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.