feat: publish training systems deep dive

2026-07-29 01:26:38 +08:00
parent c3e1e85c67
commit c6306fe260
14 changed files with 3053 additions and 41 deletions
@@ -13,6 +13,7 @@ const items = [
  { id: "moe", href: "/moe/", label: "MoE" },
  { id: "long-context", href: "/long-context/", label: "长上下文" },
  { id: "reasoning", href: "/reasoning/", label: "推理" },
+  { id: "training-systems", href: "/training-systems/", label: "训练系统" },
  { id: "papers", href: "/papers/", label: "论文库" },
  { id: "progress", href: "/progress/", label: "进度" },
 ];
@@ -121,16 +121,16 @@ export const chapters: Chapter[] = [
  },
  {
    number: "08",
-    slug: "systems/training",
+    slug: "training-systems",
    title: "大规模训练系统",
    kicker: "DISTRIBUTED TRAINING",
    question: "一个 2.8T 模型如何摊到成千上万张卡上？",
-    summary: "从 ZeRO、Megatron 和五类并行，走到 DeepSeek DualPipe/DeepEP 与 K3 MoonEP。",
-    status: "queued",
-    progress: 12,
-    papers: 18,
+    summary: "用九张资源账串起 ZeRO、Megatron、Expert/Context Parallel、DeepSeek DualPipe 与 K3 MoonEP/百万 Token RL。",
+    status: "published",
+    progress: 71,
+    papers: 37,
    prerequisites: ["04", "06"],
-    highlights: ["并行维度", "通信重叠", "MoonEP"],
+    highlights: ["显存字节账", "流水线与通信", "MoonEP"],
  },
  {
    number: "09",
@@ -590,6 +590,54 @@ export const papers: Paper[] = [
    contribution: "AdamW 将权重衰减与梯度更新正确解耦。",
    verified: true,
  },
+  {
+    year: 2012,
+    title: "Large Scale Distributed Deep Networks",
+    url: "https://arxiv.org/abs/1206.5533",
+    topics: ["训练系统"],
+    contribution: "DistBelief 与参数服务器奠定早期大规模分布式深度学习系统路线。",
+    verified: true,
+  },
+  {
+    year: 2014,
+    title: "One Weird Trick for Parallelizing Convolutional Neural Networks",
+    url: "https://arxiv.org/abs/1404.5997",
+    topics: ["训练系统"],
+    contribution: "系统比较数据并行、模型并行及其通信边界。",
+    verified: true,
+  },
+  {
+    year: 2016,
+    title: "Training Deep Nets with Sublinear Memory Cost",
+    url: "https://arxiv.org/abs/1604.06174",
+    topics: ["训练系统"],
+    contribution: "用 activation checkpointing 以额外计算换取 O(√n) feature-map memory。",
+    verified: true,
+  },
+  {
+    year: 2017,
+    title: "Mixed Precision Training",
+    url: "https://arxiv.org/abs/1710.03740",
+    topics: ["低精度", "训练系统"],
+    contribution: "建立 FP32 master weights、loss scaling 与 FP32 accumulation 配方。",
+    verified: true,
+  },
+  {
+    year: 2018,
+    title: "PipeDream: Fast and Efficient Pipeline Parallel DNN Training",
+    url: "https://arxiv.org/abs/1806.03377",
+    topics: ["训练系统"],
+    contribution: "以 1F1B、异步 pipeline 与 weight stashing 提高 stage 利用率。",
+    verified: true,
+  },
+  {
+    year: 2018,
+    title: "Mesh-TensorFlow: Deep Learning for Supercomputers",
+    url: "https://arxiv.org/abs/1811.02084",
+    topics: ["训练系统"],
+    contribution: "把 tensor dimension 的布局声明映射到逻辑 device mesh。",
+    verified: true,
+  },
  {
    year: 2019,
    title: "GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism",
@@ -614,6 +662,86 @@ export const papers: Paper[] = [
    contribution: "分片优化器、梯度与参数，消除数据并行状态冗余。",
    verified: true,
  },
+  {
+    year: 2021,
+    title: "Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM",
+    url: "https://arxiv.org/abs/2104.04473",
+    topics: ["训练系统"],
+    contribution: "组合 TP、PP、DP，并提出 interleaved pipeline schedule。",
+    verified: true,
+  },
+  {
+    year: 2021,
+    title: "ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning",
+    url: "https://arxiv.org/abs/2104.07857",
+    topics: ["训练系统"],
+    contribution: "把 GPU、CPU 与 NVMe 组成可带宽感知的异构训练内存层。",
+    verified: true,
+  },
+  {
+    year: 2021,
+    title: "GSPMD: General and Scalable Parallelization for ML Computation Graphs",
+    url: "https://arxiv.org/abs/2105.04663",
+    topics: ["训练系统"],
+    contribution: "用统一 SPMD 表达和 sharding propagation 扩展模型并行。",
+    verified: true,
+  },
+  {
+    year: 2021,
+    title: "Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines",
+    url: "https://arxiv.org/abs/2107.06925",
+    topics: ["训练系统"],
+    contribution: "从 pipeline 两端注入 micro-batches，降低同步流水线气泡。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training",
+    url: "https://arxiv.org/abs/2201.05596",
+    topics: ["MoE", "训练系统"],
+    contribution: "组合 data、expert 与 tensor parallel，系统优化 MoE 训练和推理。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning",
+    url: "https://arxiv.org/abs/2201.12023",
+    topics: ["训练系统"],
+    contribution: "用代价模型联合搜索 operator 内和 operator 间并行。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "Reducing Activation Recomputation in Large Transformer Models",
+    url: "https://arxiv.org/abs/2205.05198",
+    topics: ["训练系统"],
+    contribution: "以 Megatron sequence parallel 与 selective recomputation 降低激活内存和重算开销。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "Tutel: Adaptive Mixture-of-Experts at Scale",
+    url: "https://arxiv.org/abs/2206.03382",
+    topics: ["MoE", "训练系统"],
+    contribution: "让 MoE parallelism、dispatch 和 kernels 自适应模型与硬件配置。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "MegaBlocks: Efficient Sparse Training with Mixture-of-Experts",
+    url: "https://arxiv.org/abs/2211.15841",
+    topics: ["MoE", "训练系统"],
+    contribution: "用 block-sparse kernels 支持 dropless 动态 expert workloads。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel",
+    url: "https://arxiv.org/abs/2304.11277",
+    topics: ["训练系统"],
+    contribution: "总结 fully sharded 参数、梯度、状态与 prefetch 的工程实践。",
+    verified: true,
+  },
  {
    year: 2023,
    title: "DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models",
@@ -622,6 +750,39 @@ export const papers: Paper[] = [
    contribution: "沿 attention head 做 sequence parallel，扩展极长序列训练。",
    verified: true,
  },
+  {
+    year: 2024,
+    title: "Zero Bubble Pipeline Parallelism",
+    url: "https://arxiv.org/abs/2401.10241",
+    topics: ["训练系统"],
+    contribution: "拆分 input-gradient 与 weight-gradient，并在内存约束下搜索同步零气泡调度。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs",
+    url: "https://arxiv.org/abs/2402.15627",
+    topics: ["训练系统"],
+    contribution: "系统讨论 10K+ GPU 集群的并行、网络优化与可靠性。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "USP: A Unified Sequence Parallelism Approach for Long Context Generative AI",
+    url: "https://arxiv.org/abs/2405.07719",
+    topics: ["长上下文", "训练系统"],
+    contribution: "在二维 mesh 上组合 Ulysses All-to-All 与 Ring P2P。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "DeepEP: An Efficient Expert-Parallel Communication Library",
+    url: "https://github.com/deepseek-ai/DeepEP",
+    topics: ["MoE", "训练系统"],
+    contribution: "提供面向 NVLink/RDMA 的高吞吐与低延迟 expert dispatch/combine kernels。",
+    spotlight: "DeepSeek",
+    verified: true,
+  },
  {
    year: 2024,
    title: "Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving",
@@ -1055,7 +1216,7 @@ export const papers: Paper[] = [
    year: 2025,
    title: "Kimi K2: Open Agentic Intelligence",
    url: "https://arxiv.org/abs/2507.20534",
-    topics: ["MoE", "Agent", "后训练", "推理"],
+    topics: ["MoE", "训练系统", "Agent", "后训练", "推理"],
    contribution: "开放 1T MoE Agent 模型，以 verifiable gym 与 self-critique rubric 做 joint RL。",
    spotlight: "Kimi",
    verified: true,
@@ -1064,7 +1225,7 @@ export const papers: Paper[] = [
    year: 2026,
    title: "Kimi K2.5: Visual Agentic Intelligence",
    url: "https://arxiv.org/abs/2602.02276",
-    topics: ["Agent", "多模态", "推理"],
+    topics: ["训练系统", "Agent", "多模态", "推理"],
    contribution: "把视觉、工具使用和并行 Agent Swarm 纳入统一后训练。",
    spotlight: "Kimi",
    verified: true,
@@ -10,6 +10,7 @@ const routes: Record<string, string> = {
  moe: "/moe/",
  "long-context": "/long-context/",
  reasoning: "/reasoning/",
+  "training-systems": "/training-systems/",
 };

 const paths = [
@@ -80,16 +81,17 @@ const paths = [
          <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>
+          <a class="button" href="/training-systems/">训练系统专题</a>
        </div>
      </div>
      <aside class="hero-aside" aria-label="项目统计">
        <span>RESEARCH CUTOFF</span>
-        <strong>28 · 07 · 2026</strong>
+        <strong>29 · 07 · 2026</strong>
        <p>首版持续建设中，所有动态结论带日期</p>
        <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>146</b><span>关键论文索引</span></div>
+          <div><b>166</b><span>关键论文索引</span></div>
          <div><b>47p</b><span>K3 技术报告</span></div>
        </div>
      </aside>
@@ -103,6 +105,22 @@ const paths = [

  <section class="section compact release-section" id="new-chapters">
    <div class="release-grid">
+      <a class="release-card training-release" href="/training-systems/">
+        <div>
+          <p class="eyebrow"><span>NEW / CHAPTER 08</span> LARGE-SCALE TRAINING SYSTEMS</p>
+          <h2>一万张 GPU，为什么仍可能有一半在等？</h2>
+          <p>
+            用模型状态、激活、计算划分、气泡、collective、专家、上下文、数值与可靠性九张账，
+            从 ZeRO、Megatron 一路走到 DeepSeek DualPipe、Kimi MoonEP 与百万 Token Agentic RL。
+          </p>
+        </div>
+        <dl>
+          <div><dt>LINEAGE</dt><dd>2012 → 2026</dd></div>
+          <div><dt>PAPERS</dt><dd>37 个一手节点</dd></div>
+          <div><dt>LAB</dt><dd>显存 · 网格 · 气泡 · 通信</dd></div>
+        </dl>
+        <span class="release-arrow" aria-hidden="true">进入训练系统专题 →</span>
+      </a>
      <a class="release-card reasoning-release" href="/reasoning/">
        <div>
          <p class="eyebrow"><span>NEW / CHAPTER 11</span> REASONING & TEST-TIME SCALING</p>
@@ -384,9 +402,20 @@ const paths = [
      transition: transform 180ms ease, border-color 180ms ease;
    }

+    .training-release,
    .reasoning-release {
      grid-column: 1 / -1;
      min-height: 510px;
+    }
+
+    .training-release {
+      background:
+        radial-gradient(circle at 82% 18%, rgba(66, 111, 101, 0.19), transparent 30%),
+        repeating-linear-gradient(90deg, transparent 0 88px, rgba(94, 125, 117, 0.055) 88px 89px),
+        var(--paper-raised);
+    }
+
+    .reasoning-release {
      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%),
@@ -455,6 +484,7 @@ const paths = [
        padding-bottom: 76px;
      }

+      .training-release,
      .reasoning-release {
        grid-column: auto;
      }
@@ -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 146 篇论文</a>
+          <a class="button" href="/papers/">搜索全部 166 篇论文</a>
        </div>
      </section>
    </article>
@@ -15,6 +15,7 @@ const workstreams = [
  { 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: "大规模训练系统", value: 71, next: "补真实集群 traces、故障案例与精确 topology 配置" },
  { 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" },
 ];
@@ -39,7 +40,7 @@ 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>2026-07-29 00:38 CST</dd></div>
+        <div><dt>UPDATED</dt><dd>2026-07-29 01:19 CST</dd></div>
        <div><dt>MODE</dt><dd>持续迭代，不锁死版本</dd></div>
      </dl>
    </div>
@@ -49,7 +50,7 @@ const workstreams = [
    <div class="section-heading">
      <div>
        <p class="eyebrow"><span>01</span> WORKSTREAMS</p>
-        <h2>十条工作流同时推进，但不混淆“有页面”和“已核验”</h2>
+        <h2>十一条工作流同时推进，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。
@@ -86,12 +87,13 @@ 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>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>十二个原创交互视图</h3><p>K3、注意力、DeepSeek、长上下文、MoE、推理三页签，以及训练系统四页签实验。</p></article>
+      <article><span>✓</span><h3>七篇首版长文</h3><p>K3 导读、Transformer 基础、DeepSeek 谱系、长上下文、MoE、推理与训练系统专题。</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>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>训练系统深度专题</h3><p>九张账、37 个一手节点、DeepSeek/Kimi 双谱系与显存—网格—气泡—通信实验室。</p></article>
+      <article><span>✓</span><h3>166 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>
@@ -106,7 +108,7 @@ 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>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>P0</span><strong>大规模训练系统二轮</strong><p>真实集群 traces → 故障恢复 → 精确 topology / kernel 配置</p><em>案例库 + 实测边界</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>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>
@@ -150,6 +152,7 @@ const workstreams = [
      <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><time>2026-07-29</time><b>训练系统按九张账组织</b><p>把模型状态、激活、并行、气泡、通信、专家、上下文、数值与可靠性分开核算。</p></div>
    </div>
  </section>

@@ -699,7 +699,7 @@ const paperChain = [
        <h2>不要按模型榜单读，按“旧方法留下了哪堵墙”读</h2>
        <p>
          下面 30 篇构成本专题首版主干。课程中的机制、公式与数字优先回到这些一手来源；
-          更完整的 146 篇跨专题索引位于论文库。
+          更完整的 166 篇跨专题索引位于论文库。
        </p>
        <div class="paper-chain">
          {paperChain.map(([year, title, href, note], index) => (