# Run parallel api inference for QA

**URL:** <https://discuss.huggingface.co/t/run-parallel-api-inference-for-qa/12056>\
**Category:** 🤗Transformers\
**Created:** [November 19, 2021, 5:20am UTC](https://discuss.huggingface.co/t/run-parallel-api-inference-for-qa/12056 "2021-11-19T05:20:40Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Mamoon](https://avatars.discourse-cdn.com/v4/letter/m/848f3c/32.png) [@Mamoon](https://discuss.huggingface.co/u/Mamoon)\
**Post date:** [November 19, 2021, 5:20am UTC](https://discuss.huggingface.co/t/run-parallel-api-inference-for-qa/12056/1 "2021-11-19T05:20:41Z")

</div>

How can we handle the parallel request of question-answering using API inference for qa?