RandomGitUser321
RandomGitUser321
Yeah I didn't really know where to throw it. Since it was websocket API related, I figured here would be a decent spot for it since this is also an...
Lumina2 and it uses Qwen3 4b.
Try navigating to your python_embeded folder, open a command prompt there by typing cmd+enter in the folder path bar at the top, run `python.exe -s -m pip uninstall torch torchaudio...
Are you 100% sure you're using the exact same workflow setup in both tests? If you used a different sampler, it could slow things down. Like if you used euler...
Can you post screenshots of your task manager GPU usage while inferencing, for both versions? You're already offloading in both cases, but it's possible that one of them is using...
Yeah it looks like it's using roughly the same amounts of VRAM and shared RAM. I'm leaning toward it being an inference precision issue related to the PR I linked...
Clear your browser cache or try pressing ctrl+f5 to force a full reload of the page and also make sure any popup blockers/addons like uorigin are disabled for the page....