+- 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 for FLUX (/showthread.php?tid=1090)
Vector Databases discussion for FLUX - relayforge - 10-13-2026
Did a bit of testing and thought I'd post the result here.
I tried this with Phi using vLLM on B200. The headline result was better than I expected, but workstation thermals still ended up being the limiting factor.
Happy to post more details if anyone wants them.