You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
#136 should help reduce memory usage and allows turning off the cache entirely with ONNX_WEB_CACHE_MODELS=0. With that, memory usage appears to drop back to baseline between runs on Ubuntu 22, but I need to test it on Windows as well.
There are some remaining issues or limitations with the current cache:
if the cache limit is > 0, you can still exhaust memory by loading very large models
the default limit of 3 and SD v2.1 models in fp32 will easily max out a 24GB card
The text was updated successfully, but these errors were encountered:
#242 remains an issue on Windows, but is related to the DirectML runtime/drivers, and not something I can currently fix. Restarting the workers still works there.
#136 should help reduce memory usage and allows turning off the cache entirely with
ONNX_WEB_CACHE_MODELS=0
. With that, memory usage appears to drop back to baseline between runs on Ubuntu 22, but I need to test it on Windows as well.There are some remaining issues or limitations with the current cache:
The text was updated successfully, but these errors were encountered: