For models that take a long time to load
Open
Feature
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 158
Description
### Feature Idea
For models that take a long time to load, shouldn't they be retained separately when clearing GPU memory and RAM? For example, large language models loaded by DualCLIPLoader are very large and take a long time to load. Could an option be added at this node to specify the memory usage of the "remove model" setting? That's the gist of it. (Actually, I mainly want to be able to dynamically change this value at the code level so it doesn't fail to clear, but I don't want it to take a long time to load every time, especially with my limited 48GB of RAM.)
### Existing Solutions
_No response_
### Other
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.