Models always load fresh from disk now. No longer cache to ram.
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 158
Description
### Custom Node Testing
- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)
### Your question
I've got lots of ram but slower storage. Lastest versions of comfyui no longer cache models to shadow memory but load them from disk fresh every restart of the comfy process. As a result, what was once almost instant is now taking 20-30s to load. It's like comfy got optimized to use less sysram and just assumes everyone has NVME ssd.
Is there a flag to toggle this new behavior off?
### Logs
```powershell
```
### Other
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.