npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@cnife/pi-inference-speed

v0.1.1

Published

Show LLM inference speed (TPS) and TTFT in pi footer

Readme

@cnife/pi-inference-speed

在 pi 的 footer 状态行中显示当前 assistant message 的推理速度(TPS)首 token 延迟(TTFT)

功能

  • TPS:单条 assistant message 的推理速度,output tokens / 生成耗时,单位 tokens/s
  • TTFT:首 token 延迟,请求发出到首个 token(含 thinking/toolcall)到达的耗时,单位秒

Footer 格式

12.3T/s FT1.2s
  • 无数据时显示 --.-T/s FT -.-s(dim 色)
  • 每条 assistant message 结束后刷新,保持到下一条

计算口径

| 指标 | 起点 | 终点 | 公式 | |------|------|------|------| | TPS | before_provider_request(请求发出) | message_end(message 结束) | usage.output / elapsed | | TTFT | before_provider_request(请求发出) | 首个 _delta(任意 token 增量) | (firstDeltaAt - requestAt) / 1000 |

  • TPS 公式参考 tps.tsoutput/elapsedSeconds,统计范围按单条 message
  • TTFT 用流式事件精确计时,首 token 含 text_delta/thinking_delta/toolcall_delta 任意增量

事件处理

  • 切换模型 / Compaction / 树导航 / 新会话:重置为占位显示
  • 每次 assistant message 结束时刷新 TPS/TTFT
  • stopReasonaborted/error 时重置为占位

安装

pi install npm:@cnife/pi-inference-speed

使用

安装后自动生效,无需额外命令。

故障排查

| 现象 | 原因 | 解决 | |------|------|------| | Footer 显示 --.-T/s FT -.-s | 当前会话还没有有效的 assistant message | 发送一条消息后会自动更新 | | TPS 数值异常大 | 极短 message(output 少、耗时极短) | 属正常现象,长 message 会稳定 |