site_name: 'FastDeploy 2.0: Large Language Model Deployement'
nav:
  - 'FastDeploy 2.0': index.md
  - 'Quick Start':
      - Installation:
          - 'Nvidia GPU': get_started/installation/nvidia_gpu.md
          - 'KunlunXin XPU': get_started/installation/kunlunxin_xpu.md
          - 'Enflame S60': get_started/installation/Enflame_gcu.md
          - 'Iluvatar CoreX': get_started/installation/iluvatar_gpu.md
      - 'Quick Deployment For ERNIE-4.5-0.3B-Paddle': get_started/quick_start.md
      - 'Quick Deployment for ERNIE-4.5-VL-28B-A3B': get_started/quick_start_vl.md
      - 'ERNIE-4.5-300B-A47B': get_started/ernie-4.5.md
      - 'ERNIE-4.5-VL-424B-A47B': get_started/ernie-4.5-vl.md
  - 'Online Serving':
      - 'OpenAI-Compitable API Server': online_serving/README.md
      - 'Monitor Metrics': online_serving/metrics.md
      - 'Scheduler': online_serving/scheduler.md
  - 'Offline Inference': offline_inference.md
  - Quantiation:
      - 'Overview': quantization/README.md
      - 'Online Quantization': quantization/online_quantization.md
      - 'WINT2 Quantization': quantization/wint2.md
  - Features:
      - 'Prefix Caching': features/prefix_caching.md
      - 'Disaggration': features/disaggregated.md
      - 'Chunked Prefill': features/chunked_prefill.md
      - 'Load Balance': features/load_balance.md
      - 'Speculative Decoding': features/speculative_decoding.md
      - 'Structured Outputs': features/structured_outputs.md
      - 'Reasoning Output': features/reasoning_output.md
  - 'Supported Models': supported_models.md
  - Benchmark: benchmark.md
  - Usage:
      - 'Log Description': usage/log.md
      - 'Code Overview': usage/code_overview.md
      - 'Environment Variables': usage/environment_variables.md
theme:
  name: 'material'
  highlightjs: true
  icon:
    repo: fontawesome/brands/github
repo_url: https://github.com/PaddlePaddle/FastDeploy
repo_name: FastDeploy