# Hugging Face — How we sped up transformer inference 100x for 🤗 API customers

- Company: Hugging Face (huggingface.co)
- Announced: 2021-01-18
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://huggingface.co/blog/accelerated-inference
- Record: https://forck.live/items/2272-how-we-sped-up-transformer-inference-100x-for-api-customers
- Subject: Platform

Hugging Face announced that they have achieved a 100x speedup in transformer inference for their Accelerated Inference API customers through a combination of high-level optimizations using Hugging Face libraries and low-level hardware-specific compilation techniques.

## Evidence

Verbatim from https://huggingface.co/blog/accelerated-inference:

> This 100x performance gain and built-in scalability is why subscribers of our hosted Accelerated Inference API chose to build their NLP features on top of it.

---

Record: https://forck.live/items/2272-how-we-sped-up-transformer-inference-100x-for-api-customers
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md