Skip to content

Update ReadMe for torch_quant_to_onnx.py example #395

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update ReadMe for torch_quant_to_onnx.py example #395

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 2 additions & 0 deletions examples/onnx_ptq/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,6 +152,8 @@ python torch_quant_to_onnx.py \
--onnx_save_path=<path to save the exported ONNX model>
```

> *Note: TensorRT has limited support for Convolution layers with certain precision formats. FP8 Convolution layers remain restricted to specific kernel sizes and channel multiples, and there are no NVFP4 convolution kernels today—NVFP4 export is effectively limited to GEMM-heavy Transformer-style models (e.g., ViT). Convolution-centric CNNs such as ResNet, ConvNeXt, or MobileNet will fail when exported with `quantize_mode=nvfp4|int4_awq`.*
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Will they fail to export or just export in FP16?


### Evaluation

If the input model is of type image classification, use the following script to evaluate it.
Expand Down