Tagged: optimum

5 articles

Latest

Hugging Face's 50,000 developers get plug-and-play access to Graphcore IPUs

Optimum 1.2 brings ONNX Runtime to Transformers pipelines for faster BERT inference

Intel and Hugging Face team up to slash Transformer latency to milliseconds

Hugging Face and Intel shrink ViT models 4x with one-click OpenVINO quantization

Quanto brings flexible PyTorch quantization to Optimum, no tracing required