feat: publish numerics and optimization chapter

src/data/chapters.ts

@@ -138,12 +138,12 @@ export const chapters: Chapter[] = [
     title: "数值精度、优化器与稳定性",
     kicker: "OPTIMIZATION",
     question: "为什么少几个比特能省巨资，也可能让训练瞬间崩掉？",
-    summary: "解释 AdamW、μP、Muon、BF16/FP8/MXFP4 与量化感知训练的数值直觉。",
-    status: "queued",
-    progress: 13,
-    papers: 16,
+    summary: "用十张数值账解释 AdamW、μP、Muon、BF16/FP8/MXFP4、QAT 与训练失稳反馈环。",
+    status: "published",
+    progress: 75,
+    papers: 36,
     prerequisites: ["02", "08"],
-    highlights: ["FP8", "Muon", "MXFP4"],
+    highlights: ["FP8", "MuonClip", "MXFP4", "稳定性控制室"],
   },
   {
     number: "10",

src/data/papers.ts

@@ -6,6 +6,7 @@ export type PaperTopic =
   | "Scaling"
   | "数据"
   | "训练系统"
+  | "优化器"
   | "低精度"
   | "后训练"
   | "推理"
@@ -867,7 +868,7 @@ export const papers: Paper[] = [
     year: 2014,
     title: "Adam: A Method for Stochastic Optimization",
     url: "https://arxiv.org/abs/1412.6980",
-    topics: ["训练系统"],
+    topics: ["训练系统", "优化器"],
     contribution: "自适应一阶/二阶矩估计，成为 LLM 优化器基线。",
     verified: true,
   },
@@ -875,7 +876,7 @@ export const papers: Paper[] = [
     year: 2017,
     title: "Decoupled Weight Decay Regularization",
     url: "https://arxiv.org/abs/1711.05101",
-    topics: ["训练系统"],
+    topics: ["训练系统", "优化器"],
     contribution: "AdamW 将权重衰减与梯度更新正确解耦。",
     verified: true,
   },
@@ -1081,11 +1082,19 @@ export const papers: Paper[] = [
     spotlight: "Kimi",
     verified: true,
   },
+  {
+    year: 2024,
+    title: "Muon: An Optimizer for Hidden Layers in Neural Networks",
+    url: "https://kellerjordan.github.io/posts/muon/",
+    topics: ["优化器"],
+    contribution: "把 momentum matrix 经 Newton–Schulz 近似正交化，给出 Muon 的原始定义与参考实现。",
+    verified: true,
+  },
   {
     year: 2025,
     title: "Muon is Scalable for LLM Training",
     url: "https://arxiv.org/abs/2502.16982",
-    topics: ["训练系统"],
+    topics: ["训练系统", "优化器"],
     contribution: "补足 Muon 在 LLM 规模的权重衰减与更新尺度配方。",
     spotlight: "Kimi",
     verified: true,
@@ -1130,6 +1139,166 @@ export const papers: Paper[] = [
     contribution: "基于近似二阶信息逐层量化大模型权重。",
     verified: true,
   },
+  {
+    year: 2015,
+    title: "Deep Learning with Limited Numerical Precision",
+    url: "https://arxiv.org/abs/1502.02551",
+    topics: ["低精度"],
+    contribution: "系统研究定点低精度训练，并用 stochastic rounding 保住微小更新的长期积累。",
+    verified: true,
+  },
+  {
+    year: 2017,
+    title: "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference",
+    url: "https://arxiv.org/abs/1712.05877",
+    topics: ["低精度"],
+    contribution: "建立 fake quantization 与量化感知训练的经典整数推理配方。",
+    verified: true,
+  },
+  {
+    year: 2018,
+    title: "Shampoo: Preconditioned Stochastic Tensor Optimization",
+    url: "https://arxiv.org/abs/1802.09568",
+    topics: ["优化器"],
+    contribution: "沿 tensor 各 mode 构造结构化预条件器，在逐坐标自适应之外利用矩阵几何。",
+    verified: true,
+  },
+  {
+    year: 2018,
+    title: "Adafactor: Adaptive Learning Rates with Sublinear Memory Cost",
+    url: "https://arxiv.org/abs/1804.04235",
+    topics: ["优化器", "训练系统"],
+    contribution: "用行列因子近似二阶矩，并以 update clipping 降低优化器状态与失稳风险。",
+    verified: true,
+  },
+  {
+    year: 2019,
+    title: "A Study of BFLOAT16 for Deep Learning Training",
+    url: "https://arxiv.org/abs/1905.12322",
+    topics: ["低精度", "训练系统"],
+    contribution: "解释 BF16 保留 FP32 exponent、压缩 mantissa 的范围—精度取舍。",
+    verified: true,
+  },
+  {
+    year: 2020,
+    title: "Query-Key Normalization for Transformers",
+    url: "https://arxiv.org/abs/2010.04245",
+    topics: ["Transformer", "优化器"],
+    contribution: "归一化每个 attention head 的 Q/K 并学习缩放，直接约束 Softmax logit 尺度。",
+    verified: true,
+  },
+  {
+    year: 2021,
+    title: "8-bit Optimizers via Block-wise Quantization",
+    url: "https://arxiv.org/abs/2110.02861",
+    topics: ["优化器", "低精度"],
+    contribution: "用 block-wise dynamic quantization 压缩 optimizer state，同时隔离离群值影响。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "DeepNet: Scaling Transformers to 1,000 Layers",
+    url: "https://arxiv.org/abs/2203.00555",
+    topics: ["Transformer", "优化器"],
+    contribution: "用 DeepNorm 的残差缩放与初始化界约束深层 Transformer 更新。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer",
+    url: "https://arxiv.org/abs/2203.03466",
+    topics: ["Scaling", "优化器"],
+    contribution: "μP 让小代理模型调出的超参数可随宽度迁移到更大网络。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Scaling Vision Transformers to 22 Billion Parameters",
+    url: "https://arxiv.org/abs/2302.05442",
+    topics: ["Transformer", "优化器", "多模态"],
+    contribution: "以 QK LayerNorm 等改动缓解超大 ViT 的 attention logit 爆炸。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Stable and Low-precision Training for Large-scale Vision-language Models",
+    url: "https://arxiv.org/abs/2304.13013",
+    topics: ["低精度", "优化器", "多模态"],
+    contribution: "用 SwitchBack 与稳定性诊断研究低精度 VLM 训练中的 outlier 和 Adam second-moment spike。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "QLoRA: Efficient Finetuning of Quantized LLMs",
+    url: "https://arxiv.org/abs/2305.14314",
+    topics: ["低精度", "后训练"],
+    contribution: "以 NF4、double quantization 和 paged optimizers 微调冻结的 4-bit 基座。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "LLM-QAT: Data-Free Quantization Aware Training for Large Language Models",
+    url: "https://arxiv.org/abs/2305.17888",
+    topics: ["低精度", "后训练"],
+    contribution: "用自生成数据进行 weight、activation 与 KV cache 的量化感知训练。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Small-scale Proxies for Large-scale Transformer Training Instabilities",
+    url: "https://arxiv.org/abs/2309.14322",
+    topics: ["优化器", "训练系统"],
+    contribution: "用高学习率小模型代理复现大模型失稳，降低稳定性机制的研究成本。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "FP8-LM: Training FP8 Large Language Models",
+    url: "https://arxiv.org/abs/2310.18313",
+    topics: ["低精度", "训练系统"],
+    contribution: "把 FP8 扩展到计算、优化器与分布式通信的端到端 LLM 训练。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Spike No More: Stabilizing the Pre-training of Large Language Models",
+    url: "https://arxiv.org/abs/2312.16903",
+    topics: ["优化器", "Transformer"],
+    contribution: "从“小 sublayer、大 shortcut”原则解释并抑制预训练早期 loss spike。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Deconstructing What Makes a Good Optimizer for Language Models",
+    url: "https://arxiv.org/abs/2407.07972",
+    topics: ["优化器"],
+    contribution: "拆解 Adam、Adafactor、Lion 等方法的更新尺度、方向与超参边界。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Scaling FP8 Training to Trillion-Token LLMs",
+    url: "https://arxiv.org/abs/2409.12517",
+    topics: ["低精度", "训练系统"],
+    contribution: "研究万亿 Token 长程 FP8 训练的 SwiGLU outlier，并提出 Smooth-SwiGLU。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "FP4 All the Way: Fully Quantized Training of LLMs",
+    url: "https://arxiv.org/abs/2505.19115",
+    topics: ["低精度", "训练系统"],
+    contribution: "探索权重、激活与梯度广泛采用 FP4 的 fully quantized 训练边界。",
+    verified: true,
+  },
+  {
+    year: 2026,
+    title: "PowLU: Power-Law Units for Stable and Efficient LLM Training",
+    url: "https://arxiv.org/abs/2605.25704",
+    topics: ["优化器", "低精度", "Transformer"],
+    contribution: "用有界幂律激活控制极值，连接 activation 设计与低精度稳定性。",
+    verified: true,
+  },
   {
     year: 2023,
     title: "AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration",
@@ -1669,6 +1838,7 @@ export const paperTopics: PaperTopic[] = [
   "Scaling",
   "数据",
   "训练系统",
+  "优化器",
   "低精度",
   "后训练",
   "推理",