# Sagemaker Serverless Inference for LayoutLMv2 model

**URL:** <https://discuss.huggingface.co/t/sagemaker-serverless-inference-for-layoutlmv2-model/14186>\
**Category:** Amazon SageMaker\
**Created:** [January 28, 2022, 3:07am UTC](https://discuss.huggingface.co/t/sagemaker-serverless-inference-for-layoutlmv2-model/14186 "2022-01-28T03:07:51Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![marshmellow77](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/marshmellow77/32/3279_2.png) [@marshmellow77](https://discuss.huggingface.co/u/marshmellow77)\
**Post date:** [January 28, 2022, 6:41am UTC](https://discuss.huggingface.co/t/sagemaker-serverless-inference-for-layoutlmv2-model/14186/3 "2022-01-28T06:41:35Z")

</div>

One caveat I forgot to mention: At the moment it seems that deploying a model \>512MB to a serverless endpoint can lead to an error. Fortunately there seems to be a workaround: [Sagemaker Serverless Inference - #7 by philschmid](https://discuss.huggingface.co/t/sagemaker-serverless-inference/13246/7)

Just something to be aware of!

Cheers  
Heiko

---

_[View the full topic](https://discuss.huggingface.co/t/sagemaker-serverless-inference-for-layoutlmv2-model/14186)._