# Hugging Face — Accelerated Inference with Optimum and Transformers Pipelines

- Company: Hugging Face (huggingface.co)
- Announced: 2022-05-10
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://huggingface.co/blog/optimum-inference
- Record: https://forck.live/items/2203-accelerated-inference-with-optimum-and-transformers-pipelines
- Subject: Platform

Optimum 1.2 adds inference support with ONNX Runtime and transformers pipelines, allowing users to use the same API as Hugging Face Transformers with accelerated runtimes.

## Evidence

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

> With release of Optimum 1.2, we are adding support for inference and transformers pipelines.

---

Record: https://forck.live/items/2203-accelerated-inference-with-optimum-and-transformers-pipelines
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md