+- 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=262)
Pages:
1
2
Re: Threadripper build for inference - latentpeak22 - 09-17-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks.
Re: Threadripper build for inference - vramghost - 09-17-2026
Not sure I agree there. I get why that seems right, but on 5090 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.
Re: Threadripper build for inference - sanevault - 09-17-2026
What worked for me was pretty simple. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.