invoke-ai / invoke-ai/InvokeAI
[enhancement]: Feature Request: Add int8_convrot quantization support for Krea-2-Turbo - Raw model Description:
Open
7.0.0
enhancement
- Dominant language
- Python
- Stars
- 28.2k
- Forks
- 3k
- Avg merge
- 6d 5h
- Merged PRs (30d)
- 19
Description
### Is there an existing issue for this?
- [x] I have searched the existing issues
### Contact Details
javadzohani.1994@gmail.com
### What should this feature add?
I would like to request native support for the `int8_convrot` quantization format in InvokeAI, specifically for the Krea-2-Turbo - Krea-2-Raw model.
While FP8 is currently supported, `int8_convrot` offers significantly faster inference speeds on lower-end GPUs without compromising quality. Adding this format would greatly improve accessibility and performance for users with limited VRAM.
### Alternatives
_No response_
### Additional Content
_No response_
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.