资讯速递：Together AI Open-Sources OSCAR: An Attention-Aware 2-Bit KV Cache Quantization System for Long-Context LLM Serving

1. Together AI Open-Sources OSCAR: An Attention-Aware 2-Bit KV Cache Quantization System for Long-Context LLM Serving

原题：Together AI Open-Sources OSCAR: An Attention-Aware 2-Bit KV Cache Quantization System for Long-Context LLM Serving

内容摘要：Together AI has released OSCAR (Offline Spectral Covariance-Aware Rotation), an INT2 KV cache quantization method for long-context LLM serving. Unlike prior rotation-based approaches that apply data-oblivious Hadamard transforms, OSCAR derives separate rotations for keys and values from attention-aw…

来源：MarkTechPost | 05-26 05:24
读原文

2. AI 开发工具继续深入工程流程

原题：What ClickUp’s mass layoff tells us about the future of work

内容摘要：The nine-year-old startup is replacing hundreds of employees with thousands of AI agents.

来源：TechCrunch AI | 05-26 00:00
读原文

3. Pope Leo calls for being ‘profoundly human’ in the age of AI

原题：Pope Leo calls for being ‘profoundly human’ in the age of AI

内容摘要：Pope Leo XIV warned of the risks of AI and unconstrained technological power in his first major papal document released on Monday. Magnifica Humanitas is the pope’s manifesto on “safeguarding the human person in the time of artificial intelligence,” in which he discusses the dangers of AI-powered wa…

来源：The Verge AI | 05-25 23:05
读原文