PyTorch compile got faster?: worth it?

[plainscope50]

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.

[homelabhenry]

[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.

[thetashed24]

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.

[mellowsupply]

I don't think that's the whole story. I get why that seems right, but on M3 Max the bottleneck felt elsewhere.

[mangofield33]

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.