logo
Unified Cache Manager
Deploy
  • English
  • 简体中文
Initializing search
    ModelEngine-Group/ucm
    • Home
    • User Guide
    • Developer Guide
    • Reference
    • Benchmark
    • Toolkit
    ModelEngine-Group/ucm
    • Home
    • User Guide
      • Installation
      • Getting Started
        • vLLM (CUDA)
        • vLLM Ascend (NPU)
        • SGLang (CUDA)
        • MindIE (NPU Ascend)
      • Support Matrix
      • Deploy
      • Deployment Frameworks
        • Kubernetes
        • pyMotor
      • Model Tour
        • GLM
        • Qwen
        • DeepSeek
        • MiniMax
        • Kimi
      • Capabilities
        • Prefix Cache
      • Observability
        • Metrics
      • Diagnostics
        • Trace Mode
      • Support Matrix
      • Architecture
      • Build from Source
      • Capability Principles
      • Add Metrics
      • Extending Store
      • Contribute
      • API & Parameters
    • Benchmark
    • Toolkit
      • KV Cache Calculator
        • dev-sandbox
        • metrics-view
        • nic-monitor
        • posix-aio
        • precheck
        • Design
        • dev-sandbox

    Deploy

    Made with Material for MkDocs