feat: add inference serving chapter
This commit is contained in:
+29
-1
@@ -17,6 +17,7 @@ const routes: Record<string, string> = {
|
||||
agents: "/agents/",
|
||||
multimodal: "/multimodal/",
|
||||
"training-systems": "/training-systems/",
|
||||
"systems/inference": "/systems/inference/",
|
||||
"systems/numerics": "/systems/numerics/",
|
||||
};
|
||||
|
||||
@@ -96,6 +97,7 @@ const paths = [
|
||||
<a class="button" href="/agents/">Agent 专题</a>
|
||||
<a class="button" href="/multimodal/">原生多模态专题</a>
|
||||
<a class="button" href="/training-systems/">训练系统专题</a>
|
||||
<a class="button" href="/systems/inference/">推理服务专题</a>
|
||||
<a class="button" href="/systems/numerics/">数值与优化专题</a>
|
||||
</div>
|
||||
</div>
|
||||
@@ -106,7 +108,7 @@ 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>355</b><span>关键论文索引</span></div>
|
||||
<div><b>400</b><span>关键论文索引</span></div>
|
||||
<div><b>47p</b><span>K3 技术报告</span></div>
|
||||
</div>
|
||||
</aside>
|
||||
@@ -120,6 +122,22 @@ const paths = [
|
||||
|
||||
<section class="section compact release-section" id="new-chapters">
|
||||
<div class="release-grid">
|
||||
<a class="release-card inference-release" href="/systems/inference/">
|
||||
<div>
|
||||
<p class="eyebrow"><span>NEW / CHAPTER 14</span> MEMORY · TIME · FLEET</p>
|
||||
<h2>推理优化不是一句“更快”:显存、首字、字间、网络与 SLO 是五本不同的账</h2>
|
||||
<p>
|
||||
用十八本账从 KV Cache、PagedAttention、连续批处理、chunked prefill、量化和推测解码,
|
||||
走到 DeepSeek V2→V4 的异构状态谱系,以及 Mooncake→Kimi K3 的混合缓存、亲和路由与预算准入。
|
||||
</p>
|
||||
</div>
|
||||
<dl>
|
||||
<div><dt>LINEAGE</dt><dd>2019 → 2026</dd></div>
|
||||
<div><dt>NODES</dt><dd>62 个一手节点</dd></div>
|
||||
<div><dt>LAB</dt><dd>显存 · P/D · 推测 · 集群</dd></div>
|
||||
</dl>
|
||||
<span class="release-arrow" aria-hidden="true">从一个 Token 进入完整服务集群 →</span>
|
||||
</a>
|
||||
<a class="release-card multimodal-release" href="/multimodal/">
|
||||
<div>
|
||||
<p class="eyebrow"><span>NEW / CHAPTER 13</span> PIXELS · TOKENS · NATIVE MULTIMODALITY</p>
|
||||
@@ -545,6 +563,7 @@ const paths = [
|
||||
transition: transform 180ms ease, border-color 180ms ease;
|
||||
}
|
||||
|
||||
.inference-release,
|
||||
.agent-release,
|
||||
.alignment-release,
|
||||
.transformer-release,
|
||||
@@ -558,6 +577,14 @@ const paths = [
|
||||
min-height: 510px;
|
||||
}
|
||||
|
||||
.inference-release {
|
||||
background:
|
||||
radial-gradient(circle at 82% 18%, rgba(35, 86, 84, 0.22), transparent 31%),
|
||||
radial-gradient(circle at 60% 76%, rgba(159, 91, 52, 0.13), transparent 27%),
|
||||
repeating-linear-gradient(90deg, transparent 0 66px, rgba(35, 86, 84, 0.045) 66px 67px),
|
||||
var(--paper-raised);
|
||||
}
|
||||
|
||||
.agent-release {
|
||||
background:
|
||||
radial-gradient(circle at 82% 18%, rgba(56, 91, 128, 0.2), transparent 30%),
|
||||
@@ -688,6 +715,7 @@ const paths = [
|
||||
padding-bottom: 76px;
|
||||
}
|
||||
|
||||
.inference-release,
|
||||
.alignment-release,
|
||||
.transformer-release,
|
||||
.foundation-release,
|
||||
|
||||
Reference in New Issue
Block a user