{"type": "article", "title": "Exploiting Sparsity for Long Context Inference: Million Token on Commodity GPUs", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/exploiting-sparsity-for-long-context-inference-million-token-on-commodity-gpus", "original_source": "https://arxiv.org/abs/2502.06766", "published": "2026-07-10T09:44:24+00:00", "accessed": "2026-07-10", "id": "exploiting-sparsity-for-long-context-inference-million-token-on-commodity-gpus"}