mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-11-11 15:33:00 +08:00
Gwena Cunha
ca94c96c50
## What does this PR do? **Type of change:** Bug fix **Overview:** Loading the model with ONNX graphsurgeon after quantization and FP16 conversion results in an ONNX model with FP16 output instead of FP32 even though the Cast_to_fp32 layer was correctly placed in the graph output. This PR fixes that issue. ## Usage ```python $ python -m modelopt.onnx.quantization --onnx_path=$MODEL_NAME.onnx --high_precision_dtype=fp16 ``` ## Testing See bug 5620660. ## Before your PR is "*Ready for review*" <!-- If you haven't finished some of the above items you can still open `Draft` PR. --> - **Make sure you read and follow [Contributor guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)** and your commits are signed. - **Is this change backward compatible?**: Yes - **Did you write any new necessary tests?**: No - **Did you add or update any necessary documentation?**: No - **Did you update [Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**: No Signed-off-by: gcunhase <4861122+gcunhase@users.noreply.github.com>