skills.rest
QingHuan-6
QingHuan-6COMMUNITY
Explore all skills by this author →
GitHub

generate-profile

Profile SGLang server performance by capturing Chrome-compatible traces.

Updated May 30, 2026
Search Tags:#performance#profiling#trace#server#perfetto#sglang#chrome-tracing
One-click install
npx skills add https://github.com/QingHuan-6/SglangGen --skill generate-profile-qinghuan-6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: generate-profile
Source: https://github.com/QingHuan-6/SglangGen/tree/main/.claude/skills/generate-profile
Command: npx skills add https://github.com/QingHuan-6/SglangGen --skill generate-profile-qinghuan-6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skill profiles SGLang server performance by launching the server, validating readiness, and capturing a trace for analysis.

Core Features & Use Cases

  • End-to-end profiling: starts the server, checks readiness, runs an accuracy sanity check, and generates a Chrome-compatible trace for performance analysis.
  • Reproducible results: returns a profile directory that contains the trace and server configuration for repeatability.
  • Use Case: A developer needs to quantify startup latency and request handling efficiency to guide optimization.

Quick Start

Run the profiling workflow to produce a Chrome trace for the active SGLang server.

Frequently Asked Questions about generate-profile

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I profile SGLang server performance for request handling and startup latency?▼

You can profile SGLang server performance by launching the server, validating readiness, and capturing a trace for analysis. This end-to-end profiling quantifies startup latency and request handling efficiency to guide optimization.

How do I generate a Chrome trace for my SGLang server?▼

Generating a Chrome trace involves running the profiling workflow on your active SGLang server. The workflow checks readiness, executes an accuracy sanity check, and outputs a Chrome-compatible trace for performance analysis.

What is the best way to analyze SGLang throughput optimization using Perfetto?▼

To analyze SGLang throughput using Perfetto, capture a server trace via this profiling workflow. It returns a profile directory containing the trace and server configuration to ensure reproducible performance analysis.

Do I need CUDA-capable hardware to run an SGLang performance trace?▼

Yes, CUDA-capable hardware is required to run an SGLang performance trace. The workflow additionally requires a working SGLang installation and a tracing workflow compatible with Chrome or Perfetto.

Can I reproduce SGLang profiling results across different server configurations?▼

Yes, SGLang profiling results are reproducible because the workflow outputs a profile directory containing both the generated trace and the server configuration. This ensures repeatability for optimization analysis.

Related Skills

Explore More Software Engineering Skills→
Fridge003Fridge003
9

generate-profile

Generate a Chrome-compatible profiling trace for an SGLang server run.

Community
Advanced
inehemiasminehemiasm

perfetto-trace-analysis

Analyze Android Perfetto traces to identify root causes of latency, memory, and jank issues.

Community
Advanced
OpenMOSSOpenMOSS
410

generate-profile

Launch an SGLang server, validate readiness, and generate a Chrome-compatible profiling trace.

Official
Advanced
FutureMLS-LabFutureMLS-Lab
556

generate-profile

Generate end-to-end performance profiling traces for SGLang server runs.

Official
Intermediate