惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

云风的 BLOG
云风的 BLOG
IT之家
IT之家
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
V
Visual Studio Blog
博客园 - 司徒正美
美团技术团队
Last Week in AI
Last Week in AI
月光博客
月光博客
博客园 - 叶小钗
MongoDB | Blog
MongoDB | Blog
U
Unit 42
T
Tailwind CSS Blog
GbyAI
GbyAI
T
The Blog of Author Tim Ferriss
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
H
Hackread – Cybersecurity News, Data Breaches, AI and More
酷 壳 – CoolShell
酷 壳 – CoolShell
Google DeepMind News
Google DeepMind News
H
Help Net Security
Hugging Face - Blog
Hugging Face - Blog
爱范儿
爱范儿
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
N
Netflix TechBlog - Medium
B
Blog RSS Feed
大猫的无限游戏
大猫的无限游戏
aimingoo的专栏
aimingoo的专栏
A
About on SuperTechFans
Y
Y Combinator Blog
罗磊的独立博客
D
DataBreaches.Net
有赞技术团队
有赞技术团队
MyScale Blog
MyScale Blog
博客园_首页
博客园 - 三生石上(FineUI控件)
G
Google Developers Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
雷峰网
雷峰网
博客园 - 【当耐特】
Engineering at Meta
Engineering at Meta
博客园 - Franky
M
MIT News - Artificial intelligence
B
Blog
The Cloudflare Blog
Apple Machine Learning Research
Apple Machine Learning Research
I
InfoQ
S
SegmentFault 最新的问题
F
Fortinet All Blogs
阮一峰的网络日志
阮一峰的网络日志
Stack Overflow Blog
Stack Overflow Blog
Microsoft Security Blog
Microsoft Security Blog

Vercel News

Vercel Open Source Program: Winter 2026 cohort How Notion Workers run untrusted code at scale with Vercel Sandbox How we run Vercel's CDN in front of Discourse From idea to secure checkout in minutes with Stripe Building Slack agents can be easy Scaling redirects to infinity on Vercel Advancing Python typing Gamma builds design-first agents with Vercel How Avalara turns pipe dreams into patent-pending with v0 Keeping community human while scaling with agents How OpenEvidence built a healthcare AI that physicians actually trust Security boundaries in agentic architectures Skills Night: 69,000+ ways agents are getting smarter Video Generation with AI Gateway We Ralph Wiggumed WebStreams to make them 10x faster How Stably ships AI testing agents in hours, not weeks How we built AEO tracking for coding agents Anyone can build agents, but it takes a platform to run them Introducing Geist Pixel The Vercel AI Accelerator is back with $6m in credits Making agent-friendly pages with content negotiation The Vercel OSS Bug Bounty program is now available Introducing the new v0 Run untrusted code with Vercel Sandbox, now generally available How Stripe built a game-changing app in a single flight with v0 How Sensay went from zero to product in six weeks AGENTS.md outperforms skills in our agent evals Agent skills explained: An FAQ Testing if "bash is all you need" AWS databases are now live on the Vercel Marketplace and v0 Use Perplexity Web Search with Vercel AI Gateway Introducing: React Best Practices Nick Bogaty joins Vercel as Chief Revenue Officer How Mux shipped durable video workflows with their @mux/ai SDK How to build agents with filesystems and bash How we made v0 an effective coding agent Stopping the slow death of internal tools Building AI-Generated Pixel Trading Cards with Vercel AI Gateway We removed 80% of our agent’s tools AI SDK 6 Our $1 million hacker challenge for React2Shell Cline now runs on Vercel AI Gateway How to prompt v0 Build smarter workflows with Notion and v0 Vercel launches partner certification Inside Workflow DevKit: How framework integrations work React2Shell Security Bulletin | Vercel Knowledge Base Billions of requests: Black Friday-Cyber Monday 2025 Investing in the Python ecosystem AWS Databases coming to the Vercel Marketplace How we built the v0 iOS app Workflow Builder: Build your own workflow automation platform Vercel Open Source Program: Fall 2025 cohort Self-driving infrastructure Vercel collaborates with Google for Gemini 3 Pro Preview launch Vercel: The anti-vendor-lock-in cloud How Nous Research used BotID to block automated abuse at scale How AI Gateway runs on Fluid compute What we learned building agents at Vercel Build and deploy data applications on Snowflake with v0 BotID Deep Analysis catches a sophisticated bot network in real-time Vercel achieves TISAX AL2 compliance to serve automotive partners Bun runtime on Vercel Functions David Totten Joins Vercel to Lead Global Field Engineering Vercel Ship AI 2025 recap You can just ship agents AI agents and services on the Vercel Marketplace Built-in durability: Introducing Workflow Development Kit Zero-config backends on Vercel AI Cloud Introducing Vercel Agent: Your new Vercel teammate Update regarding Vercel service disruption on October 20, 2025 Agents at work, a partnership with Salesforce and Slack Running Next.js in ChatGPT: How to Build ChatGPT Apps Talha Tariq joins Vercel as CTO of Security Just another (Black) Friday Server rendering benchmarks: Fluid Compute and Cloudflare Workers Towards the AI Cloud: Our Series F Collaborating with Anthropic on Claude Sonnet 4.5 to power intelligent coding agents Preventing the stampede: Request collapsing in the Vercel CDN BotID uncovers hidden SEO poisoning How we made global routing faster with Bloom filters What you need to know about vibe coding Scale to one: How Fluid solves cold starts Addressing security & quality issues with MCP tools - Vercel AI agents at scale: Rox’s Vercel-powered revenue operating system Agentic Infrastructure Zero Data Retention on AI Gateway Optimizing Vercel Sandbox snapshots How Waldium made a blog platform work for humans and AI alike How FLORA shipped a creative agent on Vercel's AI stack Agent responsibly Making Turborepo 96% faster with agents, sandboxes, and humans Unified reporting for all AI Gateway usage new.website joins forces with v0 SERHANT.'s playbook for rapid AI iteration Two startups at global scale without DevOps Chat SDK brings agents to your users 360 billion tokens, 3 million customers, 6 engineers Meet the 2026 Vercel AI Accelerator Cohort Build knowledge agents without embeddings
Improving INP with React 18 and Suspense - Vercel – Vercel
Lee Robinson · 2022-08-09 · via Vercel News

4 min read

How to optimize your application's responsiveness.

Link to headingInteraction to Next Paint (INP)

Delivering a great user experience is not just about the first initial load, but also about how responsive the page is to interaction. INP helps measure this responsiveness.

A low INP means the given page was able to respond with visual feedback quickly for the majority of interactions. This is measured from the time of the first event to when the browser could show a visual update.

An INP below or at 200 milliseconds means that your page has good responsiveness.An INP below or at 200 milliseconds means that your page has good responsiveness.

An INP below or at 200 milliseconds means that your page has good responsiveness.

Keep in mind that, by default, JavaScript is single-threaded. If you’re loading a large JS script, nothing else can happen on your page until the main thread is idle—even reacting to a user’s click on a plain HTML link.

Improving INP means improving how quickly this main thread can respond to user interaction.

Link to headingHow does INP differ from FID?

FID will soon be replaced by INP as a Core Web Vital, responsible in part for ranking your application in Google Search. Let’s break down the differences between the two:

  • FID measures only the first input and browser response. INP considers the responsiveness of all user input for the duration of the page session.

  • FID only measures the delay between input and the browser starting to respond. INP measures the time between the input and the event completing in response.

  • INP additionally groups events that occur as part of the same logical user interaction, defining the interaction’s latency as the max duration of all its events.

Let’s explore some practical solutions to lower INP with React, like selective hydration with Suspense. These techniques can also improve other metrics such as FID, Total Blocking Time (TBT), and Time to Interactive (TTI).

Link to headingReact 18 and Selective Hydration

React 18 was designed to help improve interactivity with features like selective hydration and startTransition. Concurrent React is able to prioritize what you interact with and is interruptible if higher-priority interactions occur.

React and Next.js are able to generate HTML on the server and send it to the client. The initial rendered HTML is not interactive until the JavaScript for the page has been fetched and loaded. Hydration then makes your page interactive through JavaScript (e.g. attaching event handlers to a button).

Before React (17 and lower) is able to hydrate any of the components, JavaScript for the entire page needs to be fetched. During this period, the page is not interactive. For example:

// JavaScript for the entire page must be loaded

// before the page can become interactive

export default function HomePage() {

return (

<>

<Header />

<Body />

<Footer />

</>

);

}

JavaScript for the entire page must be loaded before the page can become interactive.

With React 18, you can take hydration off the main thread and make it non-blocking, simply by creating a Suspense boundary.

You no longer have to wait for all the JavaScript to load to start hydrating parts of the page. This means components can become interactive faster by allowing the browser to do other work at the same time as hydration, making your page more responsive and resulting in lower FID and INP.

import { Suspense } from 'react';

// Using a loading component as the Suspense fallback

function Loading() { ... }

// Using `Suspense` makes hydration non-blocking

export default function HomePage() {

return (

<>

<Header />

<Suspense fallback={<Loading />}>

<Body />

<Footer />

</Suspense>

</>

);

}

Using Suspense makes hydration non-blocking with React 18.

These changes help improve the interactivity of all React applications.

Link to headingCase Study: Next.js Site

We were able to reduce the Total Blocking Time (TBT) of nextjs.org from 430ms to 80ms using selective hydration with Suspense while validating changes with Lighthouse (”lab” metrics).

// Simplified version of the changes made to

// the nextjs.org landing page to improve INP with `Suspense`

export default function Index() {

return (

<Page title="Next.js by Vercel - The React Framework">

<SkipNavContent />

<Banner badge="New" href="/blog/next-12-2">

{"Next.js 12.2 →"}

</Banner>

<Hero />

<Suspense fallback={<Loading />}>

<Features />

<Customers />

<Learn />

<Newsletter />

<Footer />

</Suspense>

</Page>

);

}

Simplified version of the changes made to the nextjs.org landing page to improve INP with Suspense.

You can omit the Suspense fallback, but proceed with caution. If any components in the subtree suspend, you risk showing a broken, empty state.

Adding Suspense to group major areas of the page allows these components to be hydrated independently. Experiment with wrapping major blocks of your site with Suspense to achieve similar results.

After rolling out these changes to production, we saw Vitals ("field" metrics) improve to:

  • First Input Delay: 5ms (Good)

  • Interaction to Next Paint: 48ms (Good)

Interaction to Next Paint (INP) of nextjs.org from Vercel Analytics.Interaction to Next Paint (INP) of nextjs.org from Vercel Analytics.

Interaction to Next Paint (INP) of nextjs.org from Vercel Analytics.

For Next.js developers, we're also working to add support for route transitions (using React 18's startTransition) with the new layouts and routing changes. This enables navigations to be interruptable if higher priority events occur, leading to further responsiveness.

Link to headingOther ways to optimize INP

Since the main thread must be idle in order to process event handlers, you can also look into these techniques to optimize INP:

You can start measuring INP today inside Vercel Speed Insights, which gives you real-time information from your real users about how your site is performing. This enables you to quickly debug performance issues and focus on what optimizations are working.