Posts: 76
Threads: 12
Joined: Aug 2026
Reputation:
0
Maybe, but I had the opposite result. 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.
I'm happy to test one more variant if you want a second data point.
Posts: 62
Threads: 4
Joined: Sep 2026
Reputation:
0
I don't think that's the whole story. 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.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps. I keep promising myself this is the last rebuild.
Posts: 184
Threads: 23
Joined: Sep 2026
Reputation:
0
subscribed, curious where this lands.
Mostly CUDA, sometimes wrong, usually measured
Posts: 85
Threads: 12
Joined: Aug 2026
Reputation:
0
Maybe, but I had the opposite result. I've seen people blame prefix caching when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.
LoRA tinkerer • dataset janitor