invoke-ai / invoke-ai/InvokeAI
[bug]: 6.13.6, BSOD when importing models
- Dominant language
- Python
- Stars
- 28.2k
- Forks
- 3k
- Avg merge
- 6d 5h
- Merged PRs (30d)
- 19
Description
### Is there an existing issue for this problem?
- [x] I have searched the existing issues
### Install method
Invoke's Launcher
### Operating system
Windows
### GPU vendor
Nvidia (CUDA)
### GPU model
3060 Ti
### GPU VRAM
8GB
### Version number
6.13.6
### Browser
_No response_
### System Information
MSI Tomahawk Max
Ryzen 3700X
2x16 GB RAM 3200 XMP
### What happened
Several times, as Invoke was working through a list of queued models to install, I got a BSOD indicating 0x1a MEMORY_MANAGEMENT and ntoskrnl.exe.
Memtest86 running fine. Stable Diffusion using NMKD also running fine, including model conversion.
Since I'm giving my memory a clean bill of health, I'd guess Invoke could have a bug with memory allocation?
### What you expected to happen
All models to import successfully without BSOD.
### How to reproduce the problem
Install latest Invoke 6.13.6 via Launcher.
Have a bunch of 2 and 4 GB models in a folder.
Make Invoke import all models, and wait.
### Additional context
_No response_
### Discord username
_No response_
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.