In a lot of cases, ONNX optimized models offer much better performance benefits as compared to using PyTorch models. This performance boost coupled with the pipelines offered by HuggingFace are a really great combo for delivering a great experience both in terms of inference speed and model perform…

Supporting ONNX optimized models

a-ware September 6, 2020, 5:45am 4

Very cool pipelines implementation

Topic		Replies	Views
Transformers.onnx vs optimum.onnxruntime 🤗Optimum	1	1195	September 12, 2022
Optimize large scale transformer model inference with ONNX Runtime Models	0	396	January 18, 2022
Optimizing models using ONNX Models	1	1134	October 21, 2020
Looking for help converting transformers to ONNX with HF Optimum 🤗Transformers	0	286	November 9, 2023
:rocket: Optimum Transformers: accelerated NLP pipelines with Infinity speed 🤗Transformers	4	680	March 25, 2022