feat: trace DeepSeek V2-Lite real routes
This commit is contained in:
@@ -2,6 +2,7 @@
|
||||
import BaseLayout from "@/layouts/BaseLayout.astro";
|
||||
import DeepSeekLineage from "@/components/DeepSeekLineage.astro";
|
||||
import DeepSeekLab from "@/components/DeepSeekLab.astro";
|
||||
import DeepSeekArtifactLab from "@/components/DeepSeekArtifactLab.astro";
|
||||
import { deepseekBranches, deepseekLedgers, deepseekPaperChain, deepseekWaves } from "@/data/deepseek";
|
||||
|
||||
const toc = [
|
||||
@@ -27,21 +28,22 @@ const toc = [
|
||||
["19", "v4-state", "V4:异构状态与稳定性"],
|
||||
["20", "k3", "与 K3 的继承边界"],
|
||||
["21", "lab", "四联交互实验"],
|
||||
["22", "branches", "别漏掉旁支"],
|
||||
["23", "audit", "事实、推导与教学模型"],
|
||||
["22", "artifact", "真实权重执行"],
|
||||
["23", "branches", "别漏掉旁支"],
|
||||
["24", "audit", "事实、推导与教学模型"],
|
||||
["↳", "papers", "六十节点阅读链"],
|
||||
];
|
||||
---
|
||||
|
||||
<BaseLayout
|
||||
title="DeepSeek 技术谱系深读:从 Dense、MoE、MLA 到 R1 与 V4"
|
||||
description="用二十四张问题账、十次技术转向、四个交互实验和六十个一手节点,完整理解 DeepSeek 的 MoE、MLA、FP8、DualPipe、GRPO、R1、V3.2 与 V4。"
|
||||
title="DeepSeek 技术谱系与真实权重深读:从 Dense、MoE、MLA 到 R1 与 V4"
|
||||
description="用二十四张问题账、十次技术转向、八个交互实验、真实 V2-Lite 权重 trace 和六十个一手节点,完整理解 DeepSeek 的 MoE、MLA、FP8、DualPipe、GRPO、R1、V3.2 与 V4。"
|
||||
section="deepseek"
|
||||
>
|
||||
<header class="page-hero deepseek-hero">
|
||||
<div class="page-hero-inner">
|
||||
<div>
|
||||
<p class="eyebrow"><span>SPOTLIGHT / DEEPSEEK · ROUND 02</span> ALGORITHM × SYSTEM × EVIDENCE</p>
|
||||
<p class="eyebrow"><span>SPOTLIGHT / DEEPSEEK · ROUND 03</span> ALGORITHM × SYSTEM × REAL WEIGHTS</p>
|
||||
<h1>不要背模型名<br />要看懂每次为什么转向</h1>
|
||||
<p class="lead">
|
||||
这不是七篇报告的摘要,而是一套可追问、可计算、可反驳的技术谱系:
|
||||
@@ -53,9 +55,9 @@ const toc = [
|
||||
<div><dt>SPAN</dt><dd>2024.01 → 2026.06</dd></div>
|
||||
<div><dt>LEDGERS</dt><dd>24 张问题账</dd></div>
|
||||
<div><dt>LINEAGE</dt><dd>10 次技术转向</dd></div>
|
||||
<div><dt>LABS</dt><dd>4 个可操作实验</dd></div>
|
||||
<div><dt>LABS</dt><dd>8 个可操作实验</dd></div>
|
||||
<div><dt>EVIDENCE</dt><dd>60 个一手 / 官方节点</dd></div>
|
||||
<div><dt>STATUS</dt><dd>重点专题 · 二轮深读</dd></div>
|
||||
<div><dt>STATUS</dt><dd>三轮 · 真实权重执行</dd></div>
|
||||
</dl>
|
||||
</div>
|
||||
</header>
|
||||
@@ -762,8 +764,25 @@ const toc = [
|
||||
<DeepSeekLab />
|
||||
</section>
|
||||
|
||||
<section class="article-section" id="artifact">
|
||||
<p class="eyebrow"><span>22</span> OFFICIAL WEIGHTS / EXECUTED</p>
|
||||
<h2>从“MLA 与 MoE 的概念”再往前一步:让官方 V2-Lite 权重真的跑起来</h2>
|
||||
<p class="lede">
|
||||
前面的四联实验负责建立公式与角色合同;下面的四联工件实验固定官方 revision、tokenizer、
|
||||
模型代码和 checkpoint 第一分片,在 RTX 5090 上连续执行 layer 0–6。它把真实观测、shape 推导、
|
||||
实现差距和未覆盖范围放在同一张证据图里。
|
||||
</p>
|
||||
<div class="artifact-callout">
|
||||
<article><span>X / FORWARD</span><b>7 / 27 layers</b><p>1 个 dense 层 + 6 个 MoE 层;layer 7 因跨分片停止。</p></article>
|
||||
<article><span>X / ROUTES</span><b>3,240</b><p>90 个有效 token × 6 层 × top-6 routed experts。</p></article>
|
||||
<article><span>X + D / CACHE</span><b>576 ↔ 5,120</b><p>latent 合同与 HF eager 实际展开元素,两张账同时保留。</p></article>
|
||||
<article><span>X / RERUN</span><b>31 / 31 exact</b><p>hidden hashes、MLA shapes、loads 与全部 token routes。</p></article>
|
||||
</div>
|
||||
<DeepSeekArtifactLab />
|
||||
</section>
|
||||
|
||||
<section class="article-section" id="branches">
|
||||
<p class="eyebrow"><span>22</span> THE MAIN LINE IS NOT THE WHOLE TREE</p>
|
||||
<p class="eyebrow"><span>23</span> THE MAIN LINE IS NOT THE WHOLE TREE</p>
|
||||
<h2>如果只读 V2 → V3 → R1 → V4,会漏掉五条反过来影响主线的旁支</h2>
|
||||
<div class="branch-grid">
|
||||
{deepseekBranches.map(([name, line, text, url]) => (
|
||||
@@ -783,7 +802,7 @@ const toc = [
|
||||
</section>
|
||||
|
||||
<section class="article-section" id="audit">
|
||||
<p class="eyebrow"><span>23</span> EVIDENCE AUDIT</p>
|
||||
<p class="eyebrow"><span>24</span> EVIDENCE AUDIT</p>
|
||||
<h2>同一张页面里有三种知识,它们的语气必须不同</h2>
|
||||
<div class="audit-grid">
|
||||
<article class="reported">
|
||||
@@ -837,6 +856,43 @@ const toc = [
|
||||
radial-gradient(circle at 65% 38%, rgba(84, 124, 116, 0.13), transparent 24%);
|
||||
}
|
||||
|
||||
.artifact-callout {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(4, minmax(0, 1fr));
|
||||
max-width: 980px;
|
||||
margin: 30px 0;
|
||||
border-top: 1px solid var(--line);
|
||||
border-left: 1px solid var(--line);
|
||||
}
|
||||
|
||||
.artifact-callout article {
|
||||
min-height: 155px;
|
||||
padding: 20px;
|
||||
border-right: 1px solid var(--line);
|
||||
border-bottom: 1px solid var(--line);
|
||||
background: var(--paper-raised);
|
||||
}
|
||||
|
||||
.artifact-callout span {
|
||||
display: block;
|
||||
color: var(--copper);
|
||||
font: 700 0.58rem/1 var(--mono);
|
||||
letter-spacing: 0.08em;
|
||||
}
|
||||
|
||||
.artifact-callout b {
|
||||
display: block;
|
||||
margin-top: 18px;
|
||||
font-size: 1.14rem;
|
||||
}
|
||||
|
||||
.artifact-callout p {
|
||||
margin: 11px 0 0;
|
||||
color: var(--muted);
|
||||
font-size: 0.68rem;
|
||||
line-height: 1.55;
|
||||
}
|
||||
|
||||
.moe-compare,
|
||||
.four-layer {
|
||||
display: grid;
|
||||
@@ -1674,6 +1730,7 @@ const toc = [
|
||||
.followup-grid,
|
||||
.state-machines,
|
||||
.v4-contract,
|
||||
.artifact-callout,
|
||||
.branch-grid,
|
||||
.audit-grid,
|
||||
.paper-chain.expanded {
|
||||
|
||||
Reference in New Issue
Block a user