+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: News & Industry (https://www.datasculpting.ai/inference/forumdisplay.php?fid=26)
+--- Thread: latest release actually worth attention: anyone testing this? (/showthread.php?tid=876)
latest release actually worth attention: anyone testing this? - mangowire - 10-07-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Maybe useful as a starting point: LM Studio on Threadripper box, keeping speculative decoding in mind from the start.
If someone wants the exact settings I can clean them up and post them.
Re: latest release actually worth attention: anyone testing this? - phaseshed - 10-08-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching.
Re: latest release actually worth attention: anyone testing this? - vectorpoint - 10-08-2026
A couple things I'd check first. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives.