feat: publish reasoning deep dive
This commit is contained in:
@@ -313,6 +313,7 @@ const toc = [
|
||||
增加推理计算可以转化为能力;不是“输出越长越聪明”。
|
||||
</p>
|
||||
</div>
|
||||
<a class="button primary" href="/reasoning/#deepseek">进入推理专题:从 DeepSeekMath、R1 到 DAPO / Dr.GRPO 的完整推导 →</a>
|
||||
</section>
|
||||
|
||||
<section class="article-section" id="v32">
|
||||
|
||||
+32
-1
@@ -9,6 +9,7 @@ const routes: Record<string, string> = {
|
||||
foundations: "/foundations/",
|
||||
moe: "/moe/",
|
||||
"long-context": "/long-context/",
|
||||
reasoning: "/reasoning/",
|
||||
};
|
||||
|
||||
const paths = [
|
||||
@@ -78,6 +79,7 @@ const paths = [
|
||||
<a class="button" href="/deepseek/">DeepSeek 专题</a>
|
||||
<a class="button" href="/moe/">MoE 专题</a>
|
||||
<a class="button" href="/long-context/">长上下文专题</a>
|
||||
<a class="button" href="/reasoning/">推理专题</a>
|
||||
</div>
|
||||
</div>
|
||||
<aside class="hero-aside" aria-label="项目统计">
|
||||
@@ -87,7 +89,7 @@ const paths = [
|
||||
<div class="hero-stats">
|
||||
<div><b>16</b><span>核心专题</span></div>
|
||||
<div><b>151</b><span>K3 报告来源</span></div>
|
||||
<div><b>130</b><span>关键论文索引</span></div>
|
||||
<div><b>146</b><span>关键论文索引</span></div>
|
||||
<div><b>47p</b><span>K3 技术报告</span></div>
|
||||
</div>
|
||||
</aside>
|
||||
@@ -101,6 +103,22 @@ const paths = [
|
||||
|
||||
<section class="section compact release-section" id="new-chapters">
|
||||
<div class="release-grid">
|
||||
<a class="release-card reasoning-release" href="/reasoning/">
|
||||
<div>
|
||||
<p class="eyebrow"><span>NEW / CHAPTER 11</span> REASONING & TEST-TIME SCALING</p>
|
||||
<h2>“多想一会儿”,到底把计算花到了哪里?</h2>
|
||||
<p>
|
||||
把推理拆成结果、覆盖、选择、过程、预算、优化、分布与系统八张账,
|
||||
从 CoT、verifier 与 GRPO 一路走到 DeepSeek-R1、Kimi k1.5 与 K3 MOPD。
|
||||
</p>
|
||||
</div>
|
||||
<dl>
|
||||
<div><dt>LINEAGE</dt><dd>2021 → 2026</dd></div>
|
||||
<div><dt>PAPERS</dt><dd>30 篇一手来源</dd></div>
|
||||
<div><dt>LAB</dt><dd>预算 · GRPO · 九教师</dd></div>
|
||||
</dl>
|
||||
<span class="release-arrow" aria-hidden="true">进入推理专题 →</span>
|
||||
</a>
|
||||
<a class="release-card moe-release" href="/moe/">
|
||||
<div>
|
||||
<p class="eyebrow"><span>NEW / CHAPTER 06</span> SPARSE EXPERTS</p>
|
||||
@@ -366,6 +384,15 @@ const paths = [
|
||||
transition: transform 180ms ease, border-color 180ms ease;
|
||||
}
|
||||
|
||||
.reasoning-release {
|
||||
grid-column: 1 / -1;
|
||||
min-height: 510px;
|
||||
background:
|
||||
radial-gradient(circle at 82% 18%, rgba(56, 91, 128, 0.17), transparent 30%),
|
||||
radial-gradient(circle at 63% 72%, rgba(150, 93, 58, 0.11), transparent 28%),
|
||||
var(--paper-raised);
|
||||
}
|
||||
|
||||
.release-card:hover {
|
||||
transform: translateY(-3px);
|
||||
border-color: var(--copper);
|
||||
@@ -428,6 +455,10 @@ const paths = [
|
||||
padding-bottom: 76px;
|
||||
}
|
||||
|
||||
.reasoning-release {
|
||||
grid-column: auto;
|
||||
}
|
||||
|
||||
.release-card dl {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
@@ -378,6 +378,7 @@ const toc = [
|
||||
On-policy distillation 让学生自己生成当前前缀,再在这个前缀上比较教师和学生对下一个 Token 的概率,
|
||||
形成稠密 reward。这样训练分布更贴近学生真正会访问的状态,也能自然结合 partial rollout。
|
||||
</p>
|
||||
<a class="button primary" href="/reasoning/#k3">进入推理专题:并排理解 partial rollout、reasoning effort 与 MOPD →</a>
|
||||
|
||||
<h3>部署约束直接进入后训练</h3>
|
||||
<p>
|
||||
|
||||
@@ -683,7 +683,7 @@ const paperChain = [
|
||||
<div class="next-links">
|
||||
<a class="button primary" href="/k3/#moe">回到 K3:在整机架构中定位 Stable LatentMoE →</a>
|
||||
<a class="button" href="/deepseek/">DeepSeek 完整论文谱系</a>
|
||||
<a class="button" href="/papers/">搜索全部 130 篇论文</a>
|
||||
<a class="button" href="/papers/">搜索全部 146 篇论文</a>
|
||||
</div>
|
||||
</section>
|
||||
</article>
|
||||
|
||||
@@ -7,11 +7,12 @@ const published = chapters.filter((chapter) => chapter.status === "published").l
|
||||
const researching = chapters.filter((chapter) => ["researching", "drafting"].includes(chapter.status)).length;
|
||||
|
||||
const workstreams = [
|
||||
{ label: "研究框架与规范", value: 76, next: "给 130 篇索引补充逐篇精读层级" },
|
||||
{ label: "研究框架与规范", value: 82, next: "给推理专题补逐篇图表/实验精读层级" },
|
||||
{ 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: "Kimi K3 深读", value: 64, next: "扩写 scaling / pre-training / 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: 61, next: "GRPO 完整公式与训练轨迹推导" },
|
||||
{ label: "DeepSeek 专题", value: 71, next: "补 R1 / DAPO 的逐图训练轨迹与复现对照" },
|
||||
{ label: "推理与测试时扩展", value: 76, next: "真实模型采样曲线、PRM 案例与逐篇图表精读" },
|
||||
{ label: "稀疏计算与 MoE", value: 74, next: "补充真实集群 traces 与专家特化案例" },
|
||||
{ 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" },
|
||||
@@ -38,7 +39,7 @@ 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 23:24 CST</dd></div>
|
||||
<div><dt>UPDATED</dt><dd>2026-07-29 00:38 CST</dd></div>
|
||||
<div><dt>MODE</dt><dd>持续迭代,不锁死版本</dd></div>
|
||||
</dl>
|
||||
</div>
|
||||
@@ -48,7 +49,7 @@ const workstreams = [
|
||||
<div class="section-heading">
|
||||
<div>
|
||||
<p class="eyebrow"><span>01</span> WORKSTREAMS</p>
|
||||
<h2>九条工作流同时推进,但不混淆“有页面”和“已核验”</h2>
|
||||
<h2>十条工作流同时推进,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。
|
||||
@@ -85,11 +86,12 @@ 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>五张原创交互图</h3><p>K3 三轴架构、Self-Attention Query、DeepSeek 谱系、长上下文成本与 MoE 路由实验室。</p></article>
|
||||
<article><span>✓</span><h3>五篇首版长文</h3><p>K3 导读、Transformer 基础、DeepSeek 谱系、长上下文与 MoE 专题。</p></article>
|
||||
<article><span>✓</span><h3>八个原创交互视图</h3><p>K3、注意力、DeepSeek、长上下文、MoE,以及推理预算/GRPO/MOPD 三页签实验。</p></article>
|
||||
<article><span>✓</span><h3>六篇首版长文</h3><p>K3 导读、Transformer 基础、DeepSeek 谱系、长上下文、MoE 与推理专题。</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>MoE 深度专题</h3><p>六张账、19 篇一手论文、DeepSeek/K3 主线与路由—容量—通信交互实验室。</p></article>
|
||||
<article><span>✓</span><h3>130 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>推理深度专题</h3><p>八张账、30 篇一手论文链、DeepSeek/Kimi 双主线与三页签互动实验室。</p></article>
|
||||
<article><span>✓</span><h3>146 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>
|
||||
</section>
|
||||
@@ -104,10 +106,10 @@ 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>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>P0</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>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>MoE 二轮深化</strong><p>真实负载 traces → 专家特化可解释性 → 共享专家语义</p><em>案例库 + 集群证据</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>P1</span><strong>推理二轮深化</strong><p>真实 pass@k 曲线 → PRM 失败案例 → 逐篇图表精读</p><em>案例库 + 真实 traces</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>
|
||||
</div>
|
||||
</section>
|
||||
@@ -147,6 +149,7 @@ const workstreams = [
|
||||
<div><time>2026-07-28</time><b>优先原创重绘</b><p>架构图做成可缩放 SVG/HTML,明确简化与来源。</p></div>
|
||||
<div><time>2026-07-28</time><b>双重开放许可</b><p>代码 MIT,原创文字与图 CC BY-SA 4.0。</p></div>
|
||||
<div><time>2026-07-28</time><b>自托管交付</b><p>源码公开到 git.k1412.top,网站部署到 k1412 私有基础设施。</p></div>
|
||||
<div><time>2026-07-29</time><b>推理按八张账组织</b><p>把答案、覆盖、选择、过程、预算、优化、分布与系统证据分开核算。</p></div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user