# PD 干净对照实验（2026-09-24 上午）：验证「cp2-P → dp2-D」传输路径下 dspark 是否正常。
# 用户疑问：单机六形态健康不等于 PD 链路健康，可能两边传输没对齐。
# 以已验证可用的 dockerserve-pd-{p,d}-vision.yml 为底，缩到 2+2 卡；P 加 engram host table
# （2 卡权重放不下，见 G1.9）。P=GPU4-5 端口 30020，D=GPU6-7 端口 30030，mini_lb=30004。
services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
    container_name: ds41-pd2-prefill
    shm_size: "32gb"
    ipc: host
    pid: host
    privileged: true
    network_mode: host

    environment:
      - CUDA_VISIBLE_DEVICES=4,5
      - SGLANG_RAGGED_VERIFY_MODE=static
      - MC_INTRANODE_NVLINK=true
      - MC_INTRA_NVLINK=true
      - SGLANG_MOONCAKE_SEND_AUX_TCP=1
      - SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE=1
    volumes:
      - /data:/data
      - /data/ymk/cache/sglang:/root/.cache/sglang
      - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
    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 2
      --ep-size 2
      --mem-fraction-static 0.75
      --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"}'
      --tokenizer-worker-num 8
      --host 0.0.0.0
      --port 30020
      --enable-cache-report
      --enable-metrics
      --speculative-algorithm DSPARK
      --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2.5
      --hicache-write-policy write_back
      --enable-prefill-cp
      --cp-strategy interleave
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake