# \[RFC\] Transformers Pipeline v2

**URL:** <https://discuss.huggingface.co/t/rfc-transformers-pipeline-v2/1209>\
**Category:** 🤗Transformers\
**Created:** [September 21, 2020, 10:11am UTC](https://discuss.huggingface.co/t/rfc-transformers-pipeline-v2/1209 "2020-09-21T10:11:04Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![dataiku](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/dataiku/32/2634_2.png) [@dataiku](https://discuss.huggingface.co/u/dataiku)\
**Post date:** [October 14, 2020, 9:53am UTC](https://discuss.huggingface.co/t/rfc-transformers-pipeline-v2/1209/5 "2020-10-14T09:53:33Z")

</div>

Hi,

Just an aparté on ONNX inference (cross-post from [Supporting ONNX optimized models](https://discuss.huggingface.co/t/supporting-onnx-optimized-models/891))

I’d be interested in an `nlp = pipeline("sentiment-analysis", onnx=True)` pipeline like @valhalla created, where the ONNX files are hosted on the model hub and stored in the transformers cache.

My use case is fast inference of pre-trained models on embedded applications (no network connection).

Cheers,

Alex

---

_[View the full topic](https://discuss.huggingface.co/t/rfc-transformers-pipeline-v2/1209)._