# 纯 tp2 单实例对照（2026-09-24 早）：与 dockerserve-cp2x4.yml 逐参数对齐，唯一差异 = 去掉
# --enable-prefill-cp --cp-strategy interleave（即无 CP），用于测「tp2 vs cp2」的 prefill 效率差。
# GPU 4-5(a)/6-7(b)，端口 30020/30030；2×tp2 聚合经 rr router 30003。
# 镜像/补丁挂载/L3/engram/tok8 全部与 cp2x4 相同。
x-common: &common
  image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
  shm_size: "32gb"
  ipc: host
  privileged: true
  network_mode: host
  volumes:
    - /data:/data
    - /data/ymk/cache/sglang:/root/.cache/sglang
    # 与 cp2x4 保持同一份 scheduler.py（含未 commit 的 CP idle 补丁），保证唯一变量是 CP 开关
    - /data/ymk/sglang/python/sglang/srt/managers/scheduler.py:/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py
  environment: &env
    SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE: "1"
    SGLANG_RAGGED_VERIFY_MODE: static
    MC_MS_AUTO_DISC: "0"
    MOONCAKE_MASTER: 127.0.0.1:50051
    MOONCAKE_TE_META_DATA_SERVER: P2PHANDSHAKE
    MOONCAKE_PROTOCOL: tcp
    MOONCAKE_GLOBAL_SEGMENT_SIZE: 300gb
  deploy:
    resources:
      reservations:
        devices:
          - driver: nvidia
            count: all
            capabilities: [gpu]

services:
  tp2:
    <<: *common
    container_name: ds41-tp2
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "4,5"
    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"}'
      --max-running-requests 64
      --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
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0
  b:
    <<: *common
    container_name: ds41-tp2-b
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "6,7"
    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"}'
      --max-running-requests 64
      --tokenizer-worker-num 8
      --host 0.0.0.0 --port 30030
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --enable-hierarchical-cache
      --hicache-ratio 2
      --hicache-mem-layout page_first_direct
      --hicache-io-backend direct
      --hicache-write-policy write_through
      --hicache-storage-backend mooncake
      --hicache-storage-prefetch-policy wait_complete
      --hicache-size 0