Posts: 85
Threads: 12
Joined: Aug 2026
Reputation:
0
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: FLUX, TensorRT-LLM, A6000, with a lot of attention on router policy.
Feel free to tear it apart if you see something dumb.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
LoRA tinkerer • dataset janitor
Posts: 64
Threads: 12
Joined: Sep 2026
Reputation:
0
I'd start with the simpler stack. Turns out 'just one more test' was a lie.
learning in public
Posts: 184
Threads: 23
Joined: Sep 2026
Reputation:
0
Quote:same here on my side.
That matches what I was seeing. That matches what I saw on 5090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Mostly CUDA, sometimes wrong, usually measured
Posts: 76
Threads: 12
Joined: Aug 2026
Reputation:
0
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Posts: 36
Threads: 3
Joined: Oct 2026
Reputation:
0
Not sure I agree there. I've seen people blame prefix caching when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one. The logs were somehow calmer than I was.
still benchmarking everything
Posts: 54
Threads: 7
Joined: Sep 2026
Reputation:
0
worth checking the driver first.
Posts: 30
Threads: 6
Joined: Sep 2026
Reputation:
0
I hit almost the same issue last night.
learning in public