AI Chip Architectures
A look at AI Chip Architectures. NVIDIA, AMD, TPUs, Trainium, Groq, Cerebras.
Topic
#deep-learning
5 篇笔记
前OpenAI推理负责人JT与Gemini pretrain负责人Rohan: Continue learning的未来
📝 摘要 本文是红杉资本对 Core Automation 联创 Jerry Tworek（前 OpenAI o1 reasoning 负责人）和 Rohan Anil（前 Google Gemini pretrain 负责人）的访谈。两人共同阐述了 Transformer 架构的根本局限——训练停止后无法真正持续学习——以及 Core Automation 寻找"Transformer 替代者…
22580: From GPT2 to Kimi3, Explained
Twenty-two thousand five hundred and eighty. That’s how many GPT-2 (2019) models fit inside KimiK3 (2026). We scaled up by a factor of 22,58...
Controlling Reasoning Effort in LLMs
How LLMs Learn Low-, Medium-, and High-Effort Reasoning Modes
Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction
📝 摘要 Google Research 发布了一种将 Multi-Token Prediction (MTP) 增层改造（retrofit）到已冻结的 Gemini Nano v3 生产模型上的方法，在不修改基座模型权重的前提下，大幅加速 Pixel 设备上的端侧 LLM 推理。该方法已在 Pixel 9 和 10 系列实机部署，使 AI Notification Summaries、Proo…