Inference
CUDA update broke my throughput - Printable Version

+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: NVIDIA / CUDA (https://www.datasculpting.ai/inference/forumdisplay.php?fid=31)
+--- Thread: CUDA update broke my throughput (/showthread.php?tid=336)

Pages: 1 2


Re: CUDA update broke my throughput - dockember - 09-23-2026

Interesting, I hadn't tried that. That matches what I saw on mini PC.


Re: CUDA update broke my throughput - mintforge - 09-24-2026

Interesting, I hadn't tried that. I ended up in about the same place using SGLang.


Re: CUDA update broke my throughput - edgecoast - 09-24-2026

Quote:Interesting, I hadn't tried that. I ended up in about the same place using SGLang.

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.

If you post your exact settings, people here can probably narrow it down pretty fast.


Re: CUDA update broke my throughput - audiopath66 - 09-24-2026

What worked for me was pretty simple. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.


Re: CUDA update broke my throughput - vramstream - 09-24-2026

Thanks, that helps. The pattern around quant drift has been pretty similar for me.