+- 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: driver/framework news roundup on dual 3090 (/showthread.php?tid=852)
driver/framework news roundup on dual 3090 - fastlab - 10-08-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of SGLang and A6000 felt surprisingly usable once I tuned around MoE serving.
If someone wants the exact settings I can clean them up and post them.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: driver/framework news roundup on dual 3090 - circuitkite - 10-08-2026
Quote:Thought I'd post a small recipe because a lot of threads ask similar things.
Appreciate the detail. That matches what I saw on 5090.
Re: driver/framework news roundup on dual 3090 - thetashed24 - 10-09-2026
I hit almost the same issue last night.
Re: driver/framework news roundup on dual 3090 - bytestack - 10-09-2026
worth checking the driver first.
Re: driver/framework news roundup on dual 3090 - mangowire - 10-10-2026
A couple things I'd check first. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: driver/framework news roundup on dual 3090 - audiopoint18 - 10-10-2026
That matches what I was seeing. I ended up in about the same place using PyTorch. The biggest change for me was simplifying the stack instead of adding one more optimization layer.