From the source
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.
From the source
From the source

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.
From the source
With release of Optimum 1.2, we are adding support for inference and transformers pipelines.
huggingface.co