Posts: 41
Threads: 7
Joined: Sep 2026
Reputation:
0
Tried to reproduce it just now. On GB200 with PyTorch, I saw basically the same behavior.
curious and caffeinated
Posts: 22
Threads: 1
Joined: Sep 2026
Reputation:
0
following this because I'm in the same boat.
Posts: 38
Threads: 7
Joined: Oct 2026
Reputation:
0
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Worth testing the simpler explanation before adopting the more interesting one.
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation:
0
subscribed, curious where this lands.
measure twice, benchmark three times
