+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: PyTorch / JAX / Other Frameworks (https://www.datasculpting.ai/inference/forumdisplay.php?fid=34)
+--- Thread: PyTorch compile got faster?: worth it? (/showthread.php?tid=958)
Pages:
1
2
Re: PyTorch compile got faster?: worth it? - plainscope50 - 10-15-2026
Quote: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. Not glamoro
Maybe, but I had the opposite result. I've seen people blame quant drift when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: PyTorch compile got faster?: worth it? - homelabhenry - 10-15-2026
Quote:[quote]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. Not
My first guess would be this: If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: PyTorch compile got faster?: worth it? - thetashed24 - 10-15-2026
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality. The logs were somehow calmer than I was.
Re: PyTorch compile got faster?: worth it? - mellowsupply - 10-15-2026
I don't think that's the whole story. I get why that seems right, but on M3 Max the bottleneck felt elsewhere.
Re: PyTorch compile got faster?: worth it? - mangofield33 - 10-15-2026
Interesting, I hadn't tried that. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.