feat: publish long-context deep dive

This commit is contained in:
wuyang
2026-07-28 22:49:04 +08:00
parent 8dc62bfaec
commit 761a75d5af
13 changed files with 2788 additions and 24 deletions
+11 -9
View File
@@ -8,11 +8,12 @@ const researching = chapters.filter((chapter) => ["researching", "drafting"].inc
const workstreams = [
{ label: "研究框架与规范", value: 72, next: "给 125 篇索引补充逐篇精读层级" },
{ label: "网站设计系统", value: 86, next: "打印样式与更多通用可视化组件" },
{ label: "网站设计系统", value: 89, next: "打印样式与更多通用可视化组件" },
{ label: "Kimi K3 深读", value: 55, next: "扩写 scaling / infra 逐图笔记" },
{ label: "Transformer 基础", value: 52, next: "加入矩阵形状动画与手算练习" },
{ label: "DeepSeek 专题", value: 54, next: "MLA 与 GRPO 完整公式推导" },
{ label: "引用与事实检查", value: 48, next: "自动化外链复查与来源等级扩展" },
{ label: "DeepSeek 专题", value: 61, next: "GRPO 完整公式与训练轨迹推导" },
{ label: "长上下文专题", value: 72, next: "加入更多论文逐图笔记与真实模型配置对比" },
{ label: "引用与事实检查", value: 54, next: "自动化外链复查与来源等级扩展" },
{ label: "开源与部署", value: 100, next: "每轮保留不可变镜像、提交与回滚点" },
];
---
@@ -36,7 +37,7 @@ const workstreams = [
<div><dt>OVERALL</dt><dd>专题平均 {average}%</dd></div>
<div><dt>READABLE</dt><dd>{published} 个首版可读专题</dd></div>
<div><dt>ACTIVE</dt><dd>{researching} 个研究/写作中</dd></div>
<div><dt>UPDATED</dt><dd>2026-07-28 22:05 CST</dd></div>
<div><dt>UPDATED</dt><dd>2026-07-28 22:47 CST</dd></div>
<div><dt>MODE</dt><dd>持续迭代,不锁死版本</dd></div>
</dl>
</div>
@@ -46,7 +47,7 @@ const workstreams = [
<div class="section-heading">
<div>
<p class="eyebrow"><span>01</span> WORKSTREAMS</p>
<h2>条工作流同时推进,但不混淆“有页面”和“已核验”</h2>
<h2>条工作流同时推进,但不混淆“有页面”和“已核验”</h2>
</div>
<p class="section-lead">
内容首版优先打通全局脉络;随后每轮迭代选择一个专题推进到论文/工程层,并做独立事实复核。
@@ -74,7 +75,7 @@ const workstreams = [
<div class="section-heading">
<div>
<p class="eyebrow"><span>02</span> COMPLETED THIS ITERATION</p>
<h2>第一轮已经落地什么</h2>
<h2>当前版本已经落地什么</h2>
</div>
<p class="section-lead">下列项目都能在仓库或网站中直接检查,不是计划项。</p>
</div>
@@ -83,8 +84,9 @@ const workstreams = [
<article><span>✓</span><h3>K3 报告已结构化拆解</h3><p>47 页报告目录、151 条参考来源和架构/后训练/系统主线已经提取。</p></article>
<article><span>✓</span><h3>16 专题知识图</h3><p>从语言模型基础到评测安全,包含先修依赖和三条贯穿案例。</p></article>
<article><span>✓</span><h3>编辑式网站系统</h3><p>响应式导航、章节模板、侧栏、进度、论文链和证据提示组件。</p></article>
<article><span>✓</span><h3>张原创交互图</h3><p>K3 三轴架构、Self-Attention Query 实验与 DeepSeek 技术谱系。</p></article>
<article><span>✓</span><h3>篇首版长文</h3><p>K3 完整导读、Transformer 基础DeepSeek 论文谱系。</p></article>
<article><span>✓</span><h3>张原创交互图</h3><p>K3 三轴架构、Self-Attention QueryDeepSeek 谱系与长上下文成本实验室。</p></article>
<article><span>✓</span><h3>篇首版长文</h3><p>K3 完整导读、Transformer 基础DeepSeek 论文谱系与长上下文专题。</p></article>
<article><span>✓</span><h3>长上下文深度专题</h3><p>五张成本账、26 篇一手论文、10+ 机制图与 8 策略交互实验室。</p></article>
<article><span>✓</span><h3>125 篇关键论文索引</h3><p>覆盖 12 个专题,支持全文搜索、标签筛选与 Kimi/DeepSeek 聚光主线。</p></article>
<article><span>✓</span><h3>公开仓库与自托管发布</h3><p>源码公开到 git.k1412.top,网站由不可变镜像、Compose Manager 与 HTTPS 交付。</p></article>
</div>
@@ -100,8 +102,8 @@ const workstreams = [
</div>
<div class="queue-table">
<div class="head"><b>优先级</b><b>专题</b><b>本轮交付</b><b>完成闸门</b></div>
<div><span>P0</span><strong>长上下文与高效注意力</strong><p>FlashAttention → MLA → Delta Rule → Kimi Linear/KDA</p><em>6 张图 + 20 篇论文</em></div>
<div><span>P0</span><strong>稀疏计算与 MoE</strong><p>Switch → DeepSeekMoE → LatentMoE → Stable LatentMoE</p><em>路由模拟器 + 通信账本</em></div>
<div><span>P1</span><strong>长上下文二轮深化</strong><p>真实模型配置 → 内核细节 → 长上下文评测与失败案例</p><em>配置比较器 + 逐图论文笔记</em></div>
<div><span>P1</span><strong>推理模型与测试时扩展</strong><p>CoT → verifier → GRPO → R1 → k1.5 → K3 MOPD</p><em>奖励/预算交互图</em></div>
<div><span>P1</span><strong>大规模训练系统</strong><p>ZeRO/Megatron → Expert/Context Parallel → DualPipe/MoonEP</p><em>显存与通信计算器</em></div>
<div><span>P2</span><strong>原生多模态</strong><p>ViT/CLIP → connector VLM → Kimi-VL/MoonViT-V2</p><em>视觉 Token 流程图</em></div>