mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-11-09 09:14:17 +08:00
Luxiao Zheng
03b20e8b49
## What does this PR do? **Type of change:** Bug fix <!-- Use one of the following: Bug fix, new feature, new example, new tests, documentation. --> **Overview:** While attempting to `transformers`, `onnx`, `torch` and `modelopt`, it is shown the following: - Original `Reshape` - `Cast` - `Transpose` becomes `Reshape` - `Transpose`, so there is no required `Cast` for int4 - Global cast replacement to FP16 is not required since it will affect other Modules ## Usage <!-- You can potentially add a usage example below. --> ```python # Add a code snippet demonstrating how to use this ``` ## Testing <!-- Mention how have you tested your change if applicable. --> ## 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 <!--- If No, explain why. --> - **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 <!--- Only for new features, API changes, critical bug fixes or bw breaking changes. --> ## Additional Information <!-- E.g. related issue. --> Signed-off-by: Luxiao Zheng <luxiaoz@nvidia.com>