Standalone tree split from LLMRL/projects/kda. Includes Triton dt_bias backward fix, train_k3 --preset 0.5b, SFT, Docker runtime, and tests.
40 lines
1.3 KiB
TeX
40 lines
1.3 KiB
TeX
\documentclass[a4paper,11pt]{article}
|
||
\input{notes-macros}
|
||
|
||
\begin{document}
|
||
|
||
% ---------- 封面 ----------
|
||
\begin{titlepage}
|
||
\centering
|
||
\vspace{2cm}
|
||
{\huge\bfseries \notetitle\par}
|
||
\vspace{0.6cm}
|
||
{\Large \notesubtitle\par}
|
||
\vspace{0.8cm}
|
||
{\large \notedate\par}
|
||
\vspace{1.5cm}
|
||
\begin{tcolorbox}[width=0.88\textwidth, colback=black!2!white, colframe=black!60, sharp corners]
|
||
\textbf{项目}:\texttt{projects/kda/} — KDA 手写实现(naive recurrent → chunked → Triton)\\
|
||
\textbf{架构}:KDA + Gated MLA + Stable LatentMoE + AttnRes 深度残差 (K3-like)\\
|
||
\textbf{参考}:KDA arXiv:2510.26692; AttnRes arXiv:2603.15031; Kimi K3 architecture notes\\
|
||
\textbf{代码}:\texttt{kda/ops/}, \texttt{kda/layers/}, \texttt{kda/models/}
|
||
\end{tcolorbox}
|
||
\end{titlepage}
|
||
|
||
\tableofcontents
|
||
\newpage
|
||
|
||
\input{sections/sec-01} % KDA 递归核心
|
||
\input{sections/sec-02} % Gate 激活
|
||
\input{sections/sec-03} % 分块并行计算
|
||
\input{sections/sec-04} % GVA 分组值注意力
|
||
\input{sections/sec-05} % KDAAttention 层
|
||
\input{sections/sec-06} % Gated MLA 矩阵吸收版
|
||
\input{sections/sec-07} % SiTU-GLU 与 Stable LatentMoE
|
||
\input{sections/sec-08} % K3 混合架构
|
||
\input{sections/sec-09} % Attention Residual 深度残差
|
||
\input{sections/sec-10} % 反向传播推导
|
||
\input{sections/sec-11} % 符号表
|
||
|
||
\end{document}
|