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OpenAI revenue keeps surging as company seeks $30 billion in fresh capital
Oct 9, 2026
GPT-Image-2 prompted by THE DECODER
Update, October 9, 2026:**
OpenAI's annualized revenue rate stood at rou…
Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
Few people pay for AI, but those who do spend big
& Matthias Bastian Oct 10, 2026
Nano Banana Pro prompted by THE DECODER
Key Points
Nearly half of US consumers use AI, …
Alibaba Qwen Releases Qwen-Image-2.1-Turbo, an 8-Step 7B Image Model
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
Google's Gemini 4 "Carbon" model reportedly feels like Anthropic's Opus 5.5 coding performance
Oct 10, 2026
Gemini 4 "Argon" hasn't even shipped yet, and there are already rumors about the next performance update.**…
Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding
Decoder hidden states from different layers of large language models (LLMs) often encode complementary information. Howe…
Claude can now generate animated explainer videos and live data dashboards from text prompts
Oct 8, 2026
Anthropic launched two new beta features for Claude.** Dashboards connects data sources like BigQuery, Datab…
全球最大独立 AI 原生影视公司，要打造「AI 版 Disney」
凭《怪物史莱克》获得奥斯卡最佳改编剧本提名的编剧 Joe Stillman、《冰雪奇缘》的选角导演 Scott Muller、《鬼妈妈》的艺术指导 John Lee，选择在一部由全球最大的独立 AI 原生影视公司 **Utopai Stud…
Being mean to Claude can now get your account suspended under Anthropic's new TOS
Oct 8, 2026
GPT-Image-2 prompted by THE DECODER
Anthropic has updated its usage policy for Claude for the first time in …
OpenAI's safety crisis keeps getting worse and the company keeps making it worse
Oct 9, 2026
GPT-Image-2 prompted by THE DECODER
Key Points
OpenAI fired three safety researchers, some of whom helped in…
清华具身模型登顶全球第一！突围GPT-6、英伟达，不靠外挂和额外数据
田, 晏林* 2026-10-09 11:52:21 来源：量子位
星动纪元选择将视频预测与动作学习分阶段训练，重点不是「视频、动作一锅炖」，而是把两者「解耦」，重新「排序」。
田晏林 发自 凹非寺
量子位 | 公众号 QbitAI
好家…
Goodfire推出模型内部监测器，低成本捕捉异常AI智能体
Goodfire发布基于可解释性的监测器，直接观察AI模型内部状态而非让第二个AI复读输出，以更低成本监控智能体行为，已面向Baseten客户开放。