+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: Vector Databases (https://www.datasculpting.ai/inference/forumdisplay.php?fid=60)
+--- Thread: Vector Databases discussion on Threadripper box (/showthread.php?tid=427)
Pages:
1
2
Re: Vector Databases discussion on Threadripper box - vrambandit - 09-26-2026
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: Vector Databases discussion on Threadripper box - fastfield4 - 09-26-2026
I tested this tonight. On M3 Max with SGLang, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.