FastDeploy/mkdocs.yml

site_name: 'FastDeploy : Large Language Model Deployement'
repo_url: https://github.com/PaddlePaddle/FastDeploy
repo_name: FastDeploy

copyright: Copyright © 2025 Maintained by FastDeploy

theme:
  name: material
  highlightjs: true
  favicon: assets/images/favicon.ico
  logo: assets/images/logo.jpg
  palette:
    - media: "(prefers-color-scheme: light)" # 浅色
      scheme: default
      primary: indigo
      accent: indigo
      toggle:
        icon: material/brightness-7
        name: Switch to dark mode
    - media: "(prefers-color-scheme: dark)" # 深色
      scheme: slate
      primary: black
      accent: indigo
      toggle:
        icon: material/brightness-4
        name: Switch to system preference

plugins:
  - search
  - i18n:
      docs_structure: folder
      fallback_to_default: true
      reconfigure_material: true
      reconfigure_search: true
      languages:
        - locale: en
          default: true
          name: English
          site_name: 'FastDeploy: Large Language Model Deployement'
          build: true
          link: /FastDeploy/
        - locale: zh
          name: 简体中文
          site_name: 飞桨大语言模型推理部署工具包
          link: /FastDeploy/zh/
          nav_translations:
            FastDeploy: FastDeploy
            Quick Start: 快速入门
            Installation: 安装
            Nvidia GPU: 英伟达 GPU
            KunlunXin XPU: 昆仑芯 XPU
            HYGON DCU: 海光 DCU
            Enflame S60: 燧原 S60
            Iluvatar CoreX: 天数 CoreX
            Metax C550: 沐曦 C550
            Quick Deployment For ERNIE-4.5-0.3B: ERNIE-4.5-0.3B快速部署
            Quick Deployment for ERNIE-4.5-VL-28B-A3B: ERNIE-4.5-VL-28B-A3B快速部署
            ERNIE-4.5-300B-A47B: ERNIE-4.5-300B-A47B快速部署
            ERNIE-4.5-VL-424B-A47B: ERNIE-4.5-VL-424B-A47B快速部署
            Quick Deployment For QWEN: Qwen3-0.6b快速部署
            Online Serving: 在线服务
            OpenAI-Compitable API Server: 兼容 OpenAI 协议的服务化部署
            Monitor Metrics: 监控Metrics
            Scheduler: 调度器
            Graceful Shutdown: 服务优雅关闭
            Offline Inference: 离线推理
            Best Practices: 最佳实践
            ERNIE-4.5-0.3B: ERNIE-4.5-0.3B
            ERNIE-4.5-21B-A3B: ERNIE-4.5-21B-A3B
            ERNIE-4.5-300B-A47B: ERNIE-4.5-300B-A47B
            ERNIE-4.5-VL-28B-A3B: ERNIE-4.5-VL-28B-A3B
            ERNIE-4.5-VL-424B-A47B: ERNIE-4.5-VL-424B-A47B
            FAQ: 常见问题
            Quantization: 量化
            Overview: 概述
            Online Quantization: 在线量化
            WINT2 Quantization: WINT2量化
            Features: 特性
            Prefix Caching: 前缀缓存
            Disaggregation: 分离式部署
            Chunked Prefill: 分块预填充
            Load Balance: 负载均衡
            Speculative Decoding: 投机解码
            Structured Outputs: 结构化输出
            Reasoning Output: 思考链内容
            Early Stop: 早停功能
            Plugins: 插件机制
            Sampling: 采样策略
            MultiNode Deployment: 多机部署
            Graph Optimization: 图优化
            Data Parallelism: 数据并行
            PLAS: PLAS
            Supported Models: 支持模型列表
            Benchmark: 基准测试
            Usage: 用法
            Log Description: 日志说明
            Code Overview: 代码概述
            Environment Variables: 环境变量

nav:
  - FastDeploy: index.md
  - Quick Start:
      - Installation:
          - Nvidia GPU: get_started/installation/nvidia_gpu.md
          - KunlunXin XPU: get_started/installation/kunlunxin_xpu.md
          - HYGON DCU: get_started/installation/hygon_dcu.md
          - Enflame S60: get_started/installation/Enflame_gcu.md
          - Iluvatar CoreX: get_started/installation/iluvatar_gpu.md
          - Metax C550: get_started/installation/metax_gpu.md
      - Quick Deployment For ERNIE-4.5-0.3B: 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
      - Quick Deployment For QWEN: get_started/quick_start_qwen.md
  - Online Serving:
      - OpenAI-Compitable API Server: online_serving/README.md
      - Monitor Metrics: online_serving/metrics.md
      - Scheduler: online_serving/scheduler.md
      - Graceful Shutdown: online_serving/graceful_shutdown_service.md
  - Offline Inference: offline_inference.md
  - Best Practices:
      - ERNIE-4.5-0.3B: best_practices/ERNIE-4.5-0.3B-Paddle.md
      - ERNIE-4.5-21B-A3B: best_practices/ERNIE-4.5-21B-A3B-Paddle.md
      - ERNIE-4.5-300B-A47B: best_practices/ERNIE-4.5-300B-A47B-Paddle.md
      - ERNIE-4.5-VL-28B-A3B: best_practices/ERNIE-4.5-VL-28B-A3B-Paddle.md
      - ERNIE-4.5-VL-424B-A47B: best_practices/ERNIE-4.5-VL-424B-A47B-Paddle.md
      - FAQ: best_practices/FAQ.md
  - Quantization:
      - Overview: quantization/README.md
      - Online Quantization: quantization/online_quantization.md
      - WINT2 Quantization: quantization/wint2.md
  - Features:
      - Prefix Caching: features/prefix_caching.md
      - Disaggregation: 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
      - Early Stop: features/early_stop.md
      - Plugins: features/plugins.md
      - Sampling: features/sampling.md
      - MultiNode Deployment: features/multi-node_deployment.md
      - Graph Optimization: features/graph_optimization.md
      - Data Parallelism: features/data_parallel_service.md
      - PLAS: features/plas_attention.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