Skip to content

Support diffusion model AIDC-AI/Ovis-Image-7B quantization #1616

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lvliang-intel merged 5 commits into from
Apr 16, 2026
+5 −3
Merged

Support diffusion model AIDC-AI/Ovis-Image-7B quantization #1616

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
2227f0f
Support AIDC-AI/Ovis-Image-7B quantization
lvliang-intel Mar 25, 2026
3cfd83f
Merge branch 'main' of https://github.com/intel/auto-round into lvl/s…
lvliang-intel Mar 25, 2026
146a740
Merge branch 'main' into lvl/support_ovis_image
lvliang-intel Apr 16, 2026
3387518
Update README.md
lvliang-intel Apr 16, 2026
369d338
Merge branch 'main' into lvl/support_ovis_image
chensuyue Apr 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions auto_round/compressors/diffusion/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,15 +62,15 @@ auto-round \

### Diffusion Support Matrix

For diffusion models, currently we only validate quantizaion on the FLUX.1-dev, which involves quantizing the transformer component of the pipeline.
For diffusion models, currently we validate quantization on the following models, which involves quantizing the transformer component of the pipeline.

| Model | calibration dataset | Model Link |
|---------------|---------------------|--------------|
| black-forest-labs/FLUX.1-dev | COCO2014 | - |
| Tongyi-MAI/Z-Image | COCO2014 | - |
| Tongyi-MAI/Z-Image-Turb | COCO2014 | - |
| stepfun-ai/NextStep-1.1 | COCO2014 | - |

| AIDC-AI/Ovis-Image-7B | COCO2014 | - |


<details>
Expand Down
4 changes: 3 additions & 1 deletion auto_round/compressors/diffusion/compressor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,8 @@
output_configs = {
"FluxTransformerBlock": ["encoder_hidden_states", "hidden_states"],
"FluxSingleTransformerBlock": ["encoder_hidden_states", "hidden_states"],
"OvisImageTransformerBlock": ["encoder_hidden_states", "hidden_states"],
"OvisImageSingleTransformerBlock": ["encoder_hidden_states", "hidden_states"],
}
Comment thread
lvliang-intel marked this conversation as resolved.


Expand Down Expand Up @@ -116,7 +118,7 @@ def __init__(
pipeline_fn: callable = None,
**kwargs,
):
logger.warning("Diffusion model quantization is experimental and is only validated on Flux models.")
logger.warning("Diffusion model quantization is experimental and is only validated on a few models.")
if dataset == "NeelNanda/pile-10k":
dataset = "coco2014"
logger.warning(
Expand Down
Loading