+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: vLLM / SGLang (https://www.datasculpting.ai/inference/forumdisplay.php?fid=36)
+--- Thread: why did throughput drop after update: setup advice (/showthread.php?tid=1238)
Pages:
1
2
Re: why did throughput drop after update: setup advice - oxidemixer - 10-18-2026
My first guess would be this: On GB200, 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: why did throughput drop after update: setup advice - deltapoint17 - 10-18-2026
Quote:Interesting, I hadn't tried that. The pattern around embeddings has been pretty similar for me. I got better results once I stopped chasing one metric
Maybe, but I had the opposite result. I get why that seems right, but on dual 3090 the bottleneck felt elsewhere.
Re: why did throughput drop after update: setup advice - nanogarden - 10-18-2026
That matches what I was seeing. I ended up in about the same place using vLLM.