# dp8+tp8 单机非 PD 对照测试（2026-09-23 晚）
# 背景：3cp2+dp2 PD 部署 dspark accept 回归（32k ctx accept len 3.14→1.31，
#       见 experiments/3cp2-pd/bench-20260923.md「未决问题」）。本配置退回单机验证
#       dspark 健康度：engram host table 关闭、无 hicache L3、无 PD、无 mooncake。
# 参数基准：dockerserve-3cp2-pd.yml 的 d 服务（dp 路径），去掉 PD/L3/engram 相关。
# GPU 0-7，端口 30000，容器 ds41-dp8，project dp8
services:
  dp8:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-dp8
    shm_size: "32gb"
    ipc: host
    privileged: true
    network_mode: host
    environment:
      SGLANG_RAGGED_VERIFY_MODE: "static"
      CUDA_VISIBLE_DEVICES: "0,1,2,3,4,5,6,7"
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 8 --ep-size 8 --dp-size 8
      --enable-dp-attention --enable-dp-lm-head
      --mem-fraction-static 0.80
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 32
      --reasoning-parser auto --tool-call-parser auto
      --default-chat-template-kwargs '{"thinking": true, "reasoning_effort": "high"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30000
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5