+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Model Merging (https://www.datasculpting.ai/inference/forumdisplay.php?fid=57)
+--- Thread: do you even need a vector DB here: setup advice (/showthread.php?tid=1034)
Pages:
1
2
Re: do you even need a vector DB here: setup advice - rocmriley - 10-15-2026
Maybe, but I had the opposite result. I get why that seems right, but on 4090 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.
Re: do you even need a vector DB here: setup advice - quantyard - 10-15-2026
Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: do you even need a vector DB here: setup advice - cacheline - 10-15-2026
Thanks, that helps. That matches what I saw on 5090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: do you even need a vector DB here: setup advice - torchsupply99 - 10-15-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: do you even need a vector DB here: setup advice - sparrowghost - 10-15-2026
same here on my side.
Re: do you even need a vector DB here: setup advice - flintriver50 - 10-15-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at workstation thermals.