Google DeepMind发布设计文档驱动系统
// Design Docs Are All You Need // Banger paper from Google DeepMind, MIT, and colleagues. What a ...
Google DeepMind和MIT团队用设计文档驱动代码生成，性能建模库不再需要修补而是完全重新生成
Google DeepMind、MIT等机构研究人员提出一种新型性能建模库系统。该库主分支几乎不包含代码，而是由自然语言设计文档的有向图构成。系统通过编程子代理从文档重新生成整个实现。设计文档围绕逐步工作示例编写，为生成代理提供上下文演示。系统基于最小递归定义操作符IR和SymPy中的符号成本表达式构建。重新生成的实现能精确复现人工审核的参考模型，包括在TPU pod切片上运行的DeepSeek-V3服务。
// Design Docs Are All You Need // Banger paper from Google DeepMind, MIT, and colleagues. What a ...
// Design Docs Are All You Need // Banger paper from Google DeepMind, MIT, and colleagues. What a genuinely strange and interesting paper this one is. Here is the setup: They maintain a performance-modeling library whose main branch contains almost no code. The repository is a directed graph of natural-language design docs. Coding sub-agents regenerate the entire implementation from those docs whenever a version updates. Every human change is an edit to a doc. The premise is that ML performance modeling invalidates its own abstractions every hardware and model generation, and coding agents are now cheap enough that regenerating a library beats patching one. Two things make the regeneration reliable. The design docs are written around step-by-step worked examples, which act as in-context demonstrations for the generating agents. The system is also anchored on a minimal recursively defined operator IR with symbolic cost expressions in SymPy. Regenerated implementations reproduce hand-audited reference models to round-off precision, including DeepSeek-V3 serving on a TPU pod slice. Paper: academy.dair.ai/papers/design-… 💬 6 🔄 2 ❤️ 16 👀 2025 📊 11 ⚡
