+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Other Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=39)
+--- Thread: throughput per watt reality check for Qwen (/showthread.php?tid=1250)
Pages:
1
2
throughput per watt reality check for Qwen - deltapoint17 - 10-14-2026
Spent some time on this today and wanted to compare notes.
I've gone back and forth between vLLM and llama.cpp for Llama. The interesting difference for me has been token cost.
Trying to avoid rebuilding the whole thing twice.
Re: throughput per watt reality check for Qwen - rasterbench - 10-14-2026
Interesting, I hadn't tried that. The pattern around small local stacks has been pretty similar for me.
Re: throughput per watt reality check for Qwen - fastbench - 10-15-2026
A couple things I'd check first. 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: throughput per watt reality check for Qwen - mlxgarden - 10-15-2026
My first guess would be this: On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: throughput per watt reality check for Qwen - vrambandit - 10-15-2026
Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing. I keep promising myself this is the last rebuild.
Re: throughput per watt reality check for Qwen - mangohouse - 10-15-2026
Quote:Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of t
Appreciate the detail. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: throughput per watt reality check for Qwen - vramridge - 10-15-2026
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. At this point the real bottleneck is my patience.
Re: throughput per watt reality check for Qwen - tensorkite - 10-15-2026
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
Re: throughput per watt reality check for Qwen - kernelmike - 10-15-2026
that fixed it for me too.
Re: throughput per watt reality check for Qwen - macrolab - 10-17-2026
A couple things I'd check first. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.