+- 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 on A6000 (/showthread.php?tid=662)
Pages:
1
2
Re: Threadripper build for inference on A6000 - sanevault - 10-07-2026
subscribed, curious where this lands.
Re: Threadripper build for inference on A6000 - edgequill - 10-08-2026
What worked for me was pretty simple. On Threadripper box, 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: Threadripper build for inference on A6000 - vectorcrate98 - 10-11-2026
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.
Re: Threadripper build for inference on A6000 - edgequill - 10-13-2026
I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: Threadripper build for inference on A6000 - phasenode - 10-13-2026
My first guess would be this: If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious.