fatal : Memory allocation failure
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 158
Description
### Custom Node Testing
- [ ] 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)
### Expected Behavior
IT JUST USES TO WORK EASILY.
### Actual Behavior
Got this error and silent crash when the vae decode is working, with 128GB ram and 96GB vram. Have no idea why? How much ram does it need?
And some time it even makes PC black screen (so 128gb is not enough for decoding?). I don't understand what your memory strategy is doing actually.
### Steps to Reproduce
Using lastest commit, run a flux2 workflow
### Debug Logs
```powershell
fatal : Memory allocation failure
```
### Other
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.