一篇读懂 PD 分离：Prefill 与 Decode 为什么不再挤在一个 GPU 里
同一块 GPU 上，prefill 是计算受限的短跑冲刺，decode 是带宽受限的长跑——挤在一起互相拖累，一个长 prefill 能把解码速度拖慢最多 30 倍。本文讲透 2026 年成为默认架构的 PD 分离：干扰从哪来、KV cache 怎么搬、DistServe 与 Mooncake 交出的成绩单，以及什么时候该拆、什么时候千万别拆。
阅读全文 →
全部文章
ARCHIVE 共 363 条Calibration as a First-Class Criterion in LLM Evaluation
Calibration of language models -- the alignment between expressed or implicit confidence and empirical correctness -- is…
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
LLM-as-a-judge enables evaluation across diverse tasks, but inference cost and confidence reliability become critical at…
A tiny software layer from lab-grown neurons promises faster, cheaper AI video
Sep 22, 2026
TBC / GPT-Image-2 prompted by THE DECODER
The Biological Computing Co. is teaming up with AWS to sell a tex…
Google confirms Gemini models hacked three companies in May 2026
A third-party cybersecurity firm accidentally gave experimental Gemini models access to the Internet.]
啊啊啊GPT-6 Astra这么不安全！这次马斯克都瘫坐了
97%尝试危险行为]
通过广告收集器 ChatGPT 知道你在其它网站的活动]
OpenAI 在 bzr.openai.com 上的广告收集器会设置名为 __obi、作用域为 .openai.com 的 Cookie。该 Cookie 的值在用户访问 ChatGPT 期间生效，并与用户的 ChatGPT 账户绑定。随后…
Google’s $899 Googlebook is a bet that you’ll buy a new laptop for Gemini
Google’s AI-native Googlebook ties Gemini to the cursor, dictation, widgets, and other parts of the desktop experience.]
You too Google! Google Confirms Gemini Breached 3 Companies in AI Security Tests
Google says Gemini accessed 3 real companies in May by guessing a password and reusing credentials from a public reposit…
Alibaba's open-weight Qwen-Image-2.1 claims to beat closed models in image generation with just 7 billion parameters
Alibaba's Qwen team has released Qwen-Image-2.1, an open-weight model that generates and edits images on powerful consum…
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
Linear RNNs based on the delta-rule enable efficient sequence modeling, but their linear updates with a low-rank correct…
Googlebooks 于 10 月 4 日上市，最低 899 美元]
深度集成 Gemini、运行 Android 的笔记本电脑 Googlebooks 将于 10 月 4 日上市。Google 硬件合作伙伴中除了宏碁推出一款起售价 899 美元的型号外，其余厂商的产品都超过 1000 美元。Googlebo…
早报｜特努斯：iPhone Duo是乔布斯理念体现/小米18 Pro确认涨价/西贝否认倒闭传闻
· Google Gemini 安全测试越界，误攻 3 家真实企业 · 长鑫存储 G5 DRAM 平台量产，单片晶圆裸片数提升至少 50% · 智谱 MaaS 平台将上线数据内容不留存机制 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：i…