Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

增加并修改了首页图标 #4

Closed
wants to merge 8 commits into from
Closed

增加并修改了首页图标 #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
e4631d4
Add files via upload
yuudiiii Nov 22, 2024
7d2c7e2
Update index.tsx
yuudiiii Nov 22, 2024
ab580c5
Merge branch 'master' into master
sparanoid Nov 22, 2024
1d386b7
Delete static/img/2Memory-Management.png
yuudiiii Nov 22, 2024
a675d56
Delete static/img/1-High-efficiency.png
yuudiiii Nov 22, 2024
2b58393
Delete static/img/3-Flexible-user-friendly.png
yuudiiii Nov 22, 2024
e1d7ab0
Add files via upload
yuudiiii Nov 22, 2024
6842836
Update index.tsx
yuudiiii Nov 22, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions src/components/HomepageFeatures/index.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,25 +10,25 @@ type FeatureItem = {

const FeatureList: FeatureItem[] = [
{
title: "高效的服务吞吐量",
Svg: require("@site/static/img/undraw_docusaurus_mountain.svg").default,
title: "高效编程",
Svg: require("@site/static/img/1-High-efficiency.svg").default,
description: (
<>
vLLM 采用独特的 PagedAttention 技术和动态批处理机制，且支持并行采样、波束搜索等多种解码算法，极大提升了服务吞吐量和响应速度
</>
),
},
{
title: "内存管理大师",
Svg: require("@site/static/img/undraw_docusaurus_tree.svg").default,
title: "实时编译",
Svg: require("@site/static/img/2Memory-Management.svg").default,
description: (
<>创新的内存管理与执行架构，通过将 kv 缓存分割为若干块进行精细管理，把内存浪费控制在序列的最后一块，能实现接近最优的内存使用且支持内存共享，浪费比例低至不到 4%
</>
),
},
{
title: "灵活易用",
Svg: require("@site/static/img/undraw_docusaurus_react.svg").default,
title: "灵活的迭代空间结构",
Svg: require("@site/static/img/3-Flexible-user-friendly.svg").default,
description: (
<>
vLLM 可无缝集成各类模型，兼容 NVIDIA、AMD、Intel 等多种硬件平台 GPU 和 CPU，并提供简洁的接口和文档，易于上手
Expand Down
Loading