wuyang/llm-atlas
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: publish MoE deep dive

Browse Source
This commit is contained in:
wuyang
2026-07-28 23:32:14 +08:00
parent 761a75d5af
commit 3db826dd4a
17 changed files with 3533 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/pages/index.astro
+57 -25
View File
@@ -7,6 +7,7 @@ import { chapters, statusLabel } from "@/data/chapters";
const routes: Record<string, string> = {
roadmap: "/roadmap/",
foundations: "/foundations/",
moe: "/moe/",
"long-context": "/long-context/",
};
@@ -75,6 +76,7 @@ const paths = [
<a class="button primary" href="/roadmap/">选择学习路径 <span aria-hidden="true">↓</span></a>
<a class="button" href="/k3/">直接解剖 K3</a>
<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>
</div>
</div>
@@ -85,7 +87,7 @@ 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>125</b><span>关键论文索引</span></div>
<div><b>130</b><span>关键论文索引</span></div>
<div><b>47p</b><span>K3 技术报告</span></div>
</div>
</aside>
@@ -97,23 +99,41 @@ const paths = [
</div>
</section>
<section class="section compact release-section" id="new-long-context">
<a class="release-card" href="/long-context/">
<div>
<p class="eyebrow"><span>NEW / CHAPTER 07</span> LONG CONTEXT</p>
<h2>一百万 Token，不是一扇更大的窗</h2>
<p>
新专题把长上下文拆成计算、缓存、位置、状态容量与系统五张账单，
沿 26 篇一手论文走完 FlashAttention、MLA、Delta Rule、KDA、Kimi K3 与 DeepSeek-V4。
</p>
</div>
<dl>
<div><dt>LINEAGE</dt><dd>2019 → 2026</dd></div>
<div><dt>VISUALS</dt><dd>10+ 机制图</dd></div>
<div><dt>LAB</dt><dd>8 种策略 · 4 档长度</dd></div>
</dl>
<span class="release-arrow" aria-hidden="true">进入专题 →</span>
</a>
<section class="section compact release-section" id="new-chapters">
<div class="release-grid">
<a class="release-card moe-release" href="/moe/">
<div>
<p class="eyebrow"><span>NEW / CHAPTER 06</span> SPARSE EXPERTS</p>
<h2>2.8T 参数，不等于每个 Token 跑 2.8T</h2>
<p>
把 MoE 拆成容量、激活计算、路由、负载、通信与稳定性六张账，
从 Switch、DeepSeekMoE、Loss-Free、LatentMoE 一路走到 K3 Stable LatentMoE。
</p>
</div>
<dl>
<div><dt>LINEAGE</dt><dd>1991 → 2026</dd></div>
<div><dt>PAPERS</dt><dd>19 篇一手来源</dd></div>
<div><dt>LAB</dt><dd>8 架构 · 4 平衡策略</dd></div>
</dl>
<span class="release-arrow" aria-hidden="true">进入 MoE 专题 →</span>
</a>
<a class="release-card context-release" href="/long-context/">
<div>
<p class="eyebrow"><span>CHAPTER 07</span> LONG CONTEXT</p>
<h2>一百万 Token，不是一扇更大的窗</h2>
<p>
把长上下文拆成计算、缓存、位置、状态容量与系统五张账，
沿 26 篇一手论文走完 FlashAttention、MLA、Delta Rule、KDA、Kimi K3 与 DeepSeek-V4。
</p>
</div>
<dl>
<div><dt>LINEAGE</dt><dd>2019 → 2026</dd></div>
<div><dt>VISUALS</dt><dd>10+ 机制图</dd></div>
<div><dt>LAB</dt><dd>8 种策略 · 4 档长度</dd></div>
</dl>
<span class="release-arrow" aria-hidden="true">进入长上下文 →</span>
</a>
</div>
</section>
<section class="section" id="why">
@@ -323,12 +343,20 @@ const paths = [
padding-bottom: 0;
}
.release-grid {
display: grid;
grid-template-columns: repeat(2, minmax(0, 1fr));
gap: 22px;
}
.release-card {
position: relative;
display: grid;
grid-template-columns: minmax(0, 1.45fr) minmax(280px, 0.65fr);
gap: clamp(34px, 6vw, 90px);
padding: clamp(28px, 4vw, 58px);
grid-template-rows: 1fr auto;
gap: 28px;
min-height: 560px;
padding: clamp(28px, 3.6vw, 50px);
padding-bottom: clamp(74px, 7vw, 92px);
border: 1px solid var(--line-strong);
color: inherit;
text-decoration: none;
@@ -346,8 +374,8 @@ const paths = [
.release-card h2 {
max-width: 760px;
margin: 20px 0 18px;
font-size: clamp(2rem, 4vw, 4.2rem);
line-height: 1.03;
font-size: clamp(2rem, 3.2vw, 3.5rem);
line-height: 1.05;
}
.release-card p:not(.eyebrow) {
@@ -358,7 +386,7 @@ const paths = [
}
.release-card dl {
margin: 0 0 28px;
margin: 0;
border-top: 1px solid var(--line);
}
@@ -391,8 +419,12 @@ const paths = [
}
@media (max-width: 760px) {
.release-card {
.release-grid {
grid-template-columns: 1fr;
}
.release-card {
min-height: 0;
padding-bottom: 76px;
}