# Supporting ONNX optimized models

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsupporting-onnx-optimized-models%2F891%3E%5C
**Category:** 🤗Transformers\
**Created:** [August 27, 2020, 4:06pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsupporting-onnx-optimized-models%2F891 "2020-08-27T16:06:29Z")\
**Posts on this page:** 1\
**Showing post:** 9

<div class="post-metadata">

**Author:** ![dataiku](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/dataiku/32/2634_2.png) [@dataiku](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdataiku)%5C
**Post date:** [October 14, 2020, 9:46am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsupporting-onnx-optimized-models%2F891%2F9 "2020-10-14T09:46:40Z")

</div>

Thanks for pointing it out to [[RFC] Transformers Pipeline v2](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frfc-transformers-pipeline-v2%2F1209). That’s good to know.

For (ii) is it possible to leverage Python class inheritance features to only add/override the methods which are necessary for ONNX?

---

_[View the full topic](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsupporting-onnx-optimized-models%2F891)._