Topic
6 篇笔记
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
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...
A practitioner's guide to KV cache management. How a modern caching architecture cuts input token costs by 90% and speeds up LLM inference b...
📝 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…
五一本打算更新一年前写的开源引擎 KVCache 实现文档，但梳理下来发现，光是 KVCache 演进的理论部分就已足够撑起一篇独立文章。在 Agent 改变搜索习惯、重塑软件行业的今天，多轮交互带来的长上下文让 KVCache 持…
You must have seen it every time you use ChatGPT or Claude that the first token takes noticeably longer to appear. Then the rest stream out ...