perf-test-flagos

Official

Measure accuracy and speed of AI models.

Authorflagos-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Benchmarking AI models to quantify accuracy and performance across deployment scenarios, enabling data-driven optimization and validation.

Core Features & Use Cases

  • End-to-end benchmarks: run accuracy tests when FlagEval is available and performance tests with vLLM bench serve.
  • Multi-profile evaluation: assess five workload profiles (short/long prefill x short/long decode plus high concurrency) to capture latency, throughput, TTFT, and TPOT.

Quick Start

Start a vLLM server with your model, then run the 5-profile benchmark workflow using the included scripts to generate a combined performance report.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: perf-test-flagos
Download link: https://github.com/flagos-ai/skills/archive/main.zip#perf-test-flagos

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.