NVIDIA / NVIDIA/Model-Optimizer
the error for quantize.py
Open
@jingyu-ml is already working on this.
Since Jul 1, 2025.
bug
investigating
model support
torch.quantization
- Dominant language
- Python
- Stars
- 3.8k
- Forks
- 604
- Avg merge
- 2d 8h
- Merged PRs (30d)
- 142
Description
I ran this command：
export MODEL_NAME=sdxl-turbo
export MODEL_PATH=/tmo/data/sdxl-turbo
mkdir /onnxdir
export ONNX_DIR=/onnxdir
python quantize.py --model sdxl-turbo --override-model-path ${MODEL_PATH} --format fp4 --batch-size 1 --calib-size 8 --quant-level 1.0 --n-steps 10 --model-dtype BFloat16 --trt-high-precision-dtype BFloat16 --quantized-torch-ckpt-save-path ./${MODEL_NAME}.pt --collect-method default --onnx-dir ${ONNX_DIR}
but get that error, How should I solve this error
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.