huggingface / optimum-intel

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

https://huggingface.co/docs/optimum/main/en/intel/index

Apache License 2.0

355 stars 99 forks source link

Use int32 as default int for export #788

Open eaidova opened 1 week ago

eaidova commented 1 week ago

What does this PR do?

as discussed in https://github.com/huggingface/optimum-intel/pull/781 openvino runtime implicitly converts int64 inputs into i32. For reducing overhead internal data conversion, convert models with int32 inputs.

There is no intention to merge, just checking for understanding impact

Before submitting

[ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
[ ] Did you make sure to update the documentation with your changes?
[ ] Did you write any new necessary tests?

HuggingFaceDocBuilderDev commented 1 week ago

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.