10-18-2026, 09:42 AM
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
|
working config for 32k context for FLUX
|
|
« Next Oldest | Next Newest »
|
Users browsing this thread: 1 Guest(s)