+- 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: power delivery for 24/7 serving (/showthread.php?tid=56)
Pages:
1
2
Re: power delivery for 24/7 serving - vramport - 09-05-2026
that fixed it for me too.
Re: power delivery for 24/7 serving - batchwire - 09-08-2026
What exact setup are you running? What model, what runtime, and roughly what context size? Turns out 'just one more test' was a lie.
Re: power delivery for 24/7 serving - homelabhenry - 09-08-2026
Quote:What exact setup are you running? What model, what runtime, and roughly what context size? Turns out 'just one more test' was a lie.
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift. Not glamorous advice, but repeatable baselines save a lot of time.
Re: power delivery for 24/7 serving - stackpilot - 09-08-2026
I hit almost the same issue last night.
Re: power delivery for 24/7 serving - homelabhenry - 09-09-2026
What exact setup are you running? Is this local-only or are you routing anything externally?