{"type": "article", "title": "Testing PyTorch 2.13 MPS FlexAttention on M1 Max: Up to 7.83x Faster for Sparse Attention", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/testing-pytorch-2-13-mps-flexattention-on-m1-max-up-to-7-83x-faster-for-sparse", "original_source": "https://dev.to/kiarina/testing-pytorch-213-mps-flexattention-on-m1-max-up-to-783x-faster-for-sparse-attention-1p7d", "published": "2026-07-21T04:03:12+00:00", "accessed": "2026-07-22", "id": "testing-pytorch-2-13-mps-flexattention-on-m1-max-up-to-7-83x-faster-for-sparse"}