09-14-2026, 08:03 AM
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
|
when a plain Python stack is enough with PyTorch
|
|
09-14-2026, 08:03 AM
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
09-14-2026, 12:51 PM
Not sure I agree there. I've seen people blame router policy when the real issue was much more mundane. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
still benchmarking everything
09-15-2026, 01:04 AM
Maybe, but I had the opposite result. I get why that seems right, but on 5090 the bottleneck felt elsewhere.
09-15-2026, 02:00 AM
Quote:Maybe, but I had the opposite result. I get why that seems right, but on 5090 the bottleneck felt elsewhere. That matches what I was seeing. 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.
09-15-2026, 10:16 AM
I hit almost the same issue last night.
|
|
« Next Oldest | Next Newest »
|