# Hugging Face — Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia

- Company: Hugging Face (huggingface.co)
- Announced: 2022-03-16
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://huggingface.co/blog/bert-inferentia-sagemaker
- Record: https://forck.live/items/2221-accelerate-bert-inference-with-hugging-face-transformers-and-aws-inferentia
- Subject: Platform
- Models affected: BERT, distilbert-base-uncased-finetuned-sst-2-english

Tutorial on accelerating BERT inference with Hugging Face Transformers and AWS Inferentia on Amazon SageMaker, covering model conversion to AWS Neuron, custom inference script creation, and deployment.

## Evidence

Verbatim from https://huggingface.co/blog/bert-inferentia-sagemaker:

> In this end-to-end tutorial, you will learn how to speed up BERT inference for text classification with Hugging Face Transformers, Amazon SageMaker, and AWS Inferentia.

---

Record: https://forck.live/items/2221-accelerate-bert-inference-with-hugging-face-transformers-and-aws-inferentia
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md