Skip to content

quantizaiton config fix #26

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
dkackman merged 2 commits into from
Apr 6, 2026
Merged

quantizaiton config fix #26

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
004adda
update
dkackman Apr 5, 2026
2477e59
properly unescape quantizaiton configs
dkackman Apr 6, 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
3 changes: 2 additions & 1 deletion CLAUDE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,10 +62,11 @@ JSON workflow → schema validation → variable substitution → sequential ste
| `dw/step.py` | Step executor: generates iterations, dispatches to pipeline/task/workflow |
| `dw/pipeline_processors/pipeline.py` | Pipeline loading, components, quantization, LoRA, schedulers, offloading |
| `dw/pipeline_processors/config_objects.py` | Quantization and group offload config creation |
| `dw/tasks/task.py` | Task dispatcher (image processing, QR codes, gathering, video, segmentation, captioning, frame interpolation) |
| `dw/tasks/task.py` | Task dispatcher (image processing, QR codes, gathering, video, segmentation, captioning, text generation, diffusion upscaling, frame interpolation) |
| `dw/tasks/segment.py` | GroundingDINO + SAM2 text-prompted object segmentation |
| `dw/tasks/image_to_text.py` | Image captioning via transformers image-to-text pipeline (BLIP, BLIP-2, etc.) |
| `dw/tasks/text_generation.py` | Text generation / prompt expansion via transformers text-generation pipeline |
| `dw/tasks/diffusion_upscale.py` | Diffusion-based image upscaling via SD upscale pipelines (x2/x4) |
| `dw/tasks/interpolate_frames.py` | RIFE frame interpolation (2x/4x/8x) with vendored IFNet v4.6 |
| `dw/tasks/rife_model.py` | Vendored RIFE IFNet v4.6 architecture (MIT License, Megvii Inc.) |
| `dw/previous_results.py` | Cross-step data flow via cartesian products |
Expand Down
10 changes: 9 additions & 1 deletion dw/pipeline_processors/config_objects.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,15 @@ def get_quantization_configuration(configuration):
quantization_config_type = quantization_config["configuration"][
"config_type"
]
return quantization_config_type(**quantization_config["arguments"])
# Some quantization configs (e.g. TorchAoConfig) require argument values
# to be instances rather than classes. realize_args converts *_type keys to
# classes; instantiate them here with no args so callers can write e.g.
# "quant_type": "torchao.quantization.Int8WeightOnlyConfig" in JSON.
args = {
k: v() if isinstance(v, type) else v
for k, v in quantization_config["arguments"].items()
}
return quantization_config_type(**args)
except Exception as e:
logger.error(
f"Failed to create quantization_config: {str(e)}", exc_info=True
Expand Down
Loading