{"type":"link","version":"1.0","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2406.10774","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2406.10774.png","thumbnail_width":1200,"thumbnail_height":630}