# Hugging Face — Accelerating Hugging Face Transformers with AWS Inferentia2

- Company: Hugging Face (huggingface.co)
- Announced: 2023-04-17
- Category: partnership-acquisition
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://huggingface.co/blog/accelerate-transformers-with-inferentia2
- Record: https://forck.live/items/2074-accelerating-hugging-face-transformers-with-aws-inferentia2
- Subject: Platform
- Models affected: BERT, BERT-base, BERT-Large, RoBERTa, RoBERTa-base, DistilBERT, ALBERT, ALBERT-base, Vision Transformer, ViT, ViT-base, GPT-J-6B, Flan-T5, Opt-30B, BLOOM

Hugging Face announces a partnership with AWS to optimize Hugging Face Transformers for the new AWS Inferentia2 inference accelerator, which delivers significant improvements in throughput, latency, and performance per watt compared to previous generations and GPUs.

## Evidence

Verbatim from https://huggingface.co/blog/accelerate-transformers-with-inferentia2:

> we're excited to partner with Amazon Web Services to optimize Hugging Face Transformers for AWS Inferentia2!

---

Record: https://forck.live/items/2074-accelerating-hugging-face-transformers-with-aws-inferentia2
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md