PKC AI Project

AI๋ฅผ ํ™œ์šฉํ•˜์—ฌ ๋ณด๊ธ‰ํ˜• ๊ทธ๋ž˜ํ”ฝ ์นด๋“œ์—์„œ ๋ฉ€ํ‹ฐ๋ชจ๋‹ฌ ์ฑ—๋ด‡ ๋งŒ๋“ค์–ด ๋ณด๊ธฐ

AI MARK Benchmark/AI MARK Benchmark English Translation

PKC Benchmark Tool MARK (Public Edition) Analysis Report

AI Orchestrator 2025. 9. 27. 15:24

PKC Benchmark Tool MARK (Public Edition) Analysis Report

๐Ÿ“‹ Overview

This project is an AI model performance measurement tool. Simply put, it's a "program that tests how fast and accurately AI models operate."

 

Korean Performance Test Video: [Link]

๐ŸŽฏ Key Features

1. One-Click Installation

  • Windows: Double-click OneClick_RUN.bat
  • macOS: Double-click oneclick.command
  • Linux: Run oneclick.sh
  • → Ready to use without complex setup

2. Automatic AI Model Management

  • Search/download models from HuggingFace
  • Auto-detection of GGUF and Transformers formats
  • → No need for users to manually find and install models

3. Performance Measurement

  • Response speed (TPS - Tokens Per Second)
  • Memory usage (VRAM)
  • Time to First Token (TTFT)
  • GPU temperature/power consumption
  • → Verify actual AI model performance with numbers

4. Real-time Chat Testing

  • Direct conversation with models after benchmark completion
  • → Check not only performance metrics but also actual usability

๐Ÿ—๏ธ Technical Architecture

Backend (Server)

  • Language: Python
  • Framework: FastAPI
  • Main Role: Model loading, performance measurement, API provision

Frontend (User Interface)

  • Language: HTML + JavaScript
  • Styling: Tailwind CSS
  • Main Role: User interaction, result visualization

Installation/Execution Scripts

  • Windows: .bat batch files
  • Linux/macOS: .sh shell scripts
  • Main Role: Automatic environment setup, dependency installation

๐Ÿ“Š Supported Platforms

Operating System Support Level Notes

Windows 10/11 โœ… Full Support Recommended environment
macOS (Intel/M1/M2/M3) โœ… Full Support Metal acceleration support
Ubuntu/Debian Linux โœ… Full Support CUDA support
Other Linux โœ… Mostly Supported  

๐ŸŽฎ GPU Support

GPU Type Support Level Description

NVIDIA (CUDA) โœ… Fully Optimized RTX, GTX series
Apple Silicon โœ… Fully Optimized M1/M2/M3 Metal acceleration
CPU Only โœ… Full Support Works on all environments
AMD GPU โš ๏ธ Experimental Linux ROCm partial support

๐Ÿ”ง Core File Roles

Execution Files

  • OneClick_RUN.bat (Windows) / oneclick.sh (Linux/Mac)
    • Role: Automate all installation and execution with one click
    • Process: Create Python virtual environment → Install libraries → Start server → Open browser

Core Programs

  • benchmark_server.py
    • Role: Main server program
    • Features: Model loading, performance measurement, web API provision, HuggingFace integration
  • benchmark_canvas.html
    • Role: User interface
    • Features: Model selection, settings adjustment, result verification, chart display

Configuration Files

  • requirements.txt: List of required Python libraries
  • config_json_public.json: Program configuration values
  • models_json_public.json: Model information management

Utilities

  • install_wizard.py: GPU optimization automatic installation tool

๐ŸŒŸ Project Strengths

1. User-Friendliness

  • Minimized entry barriers with one-click installation
  • Intuitive web interface
  • Multi-language support (Korean/English)

2. Technical Completeness

  • Cross-platform support (Windows/Mac/Linux)
  • Various GPU optimizations (NVIDIA/Apple/AMD)
  • Real-time performance monitoring

3. Scalability

  • Complete HuggingFace ecosystem integration
  • Modular architecture
  • API-based design

4. Practicality

  • Provides actual performance data
  • Model comparison functionality
  • Real usability verification through chat testing

๐ŸŽฏ Target Users

  1. AI Developers: Model performance comparison and optimization
  2. Researchers: Benchmark data collection
  3. General Users: AI model experience and testing
  4. Enterprises: Production environment performance verification (license verification required)

๐Ÿ“ˆ Usage Scenarios

Development Stage

  • Performance measurement of new models
  • Hardware-specific optimization verification
  • Memory usage analysis

Research Stage

  • Performance comparison between models
  • Benchmark data collection
  • Experimental data generation for papers

Operation Stage

  • Production environment performance verification
  • Server resource planning
  • Cost-effectiveness analysis

Conclusion: This project is a highly complete tool that makes the specialized task of AI model performance measurement easily accessible to everyone. The biggest advantage is its design that allows immediate use without installation complexity.

 

The PKC Benchmark Tool will be distributed through this blog after revision work. (Though we don't know when that will be...)