sglang/deploy/b300-ds41/dockerserve-cp2x4.yml

# 4×cp2 独立实例（非 PD）+ hicache L3(mooncake) + dspark + engram host table 卸载（2026-09-23 晚）
# 用户指定组合：4 cp2 hicache l3 dspark roundrobin loadbalance engram offload
# 每实例：tp2 ep2 + interleave CP2 + dspark b5 + hicache L3 write_through(size 0) + engram host table
# （tp2 权重必须靠 engram 卸载才放得下，见 goals-track G1.9 反转）
# GPU: a=0,1 b=2,3 c=4,5 d=6,7；端口: 30000/30010/30020/30030；rr router=30002
# 参考：dockerserve-cpdspark-l3.yml（hicache 参数）、dockerserve-3cp2-pd.yml（cp2/engram 参数）
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
    # 热补丁（2026-09-23）：CP 对称 idle 检查，修 health-check × hicache drain 死锁
    # 源文件：/data/ymk/sglang（dsv41-pd-visioncp 分支工作区已改）；补丁脚本见
    # D:\B300\experiments\cp2x4\patch_healthcheck_cp_idle.py
    - /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:
  a:
    <<: *common
    container_name: ds41-cp2-a
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "0,1"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --enable-prefill-cp --cp-strategy interleave
      --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 30000
      --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-cp2-b
    environment:
      <<: *env
      CUDA_VISIBLE_DEVICES: "2,3"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2
      --enable-prefill-cp --cp-strategy interleave
      --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 30010
      --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
  c:
    <<: *common
    container_name: ds41-cp2-c
    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
      --enable-prefill-cp --cp-strategy interleave
      --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
  d:
    <<: *common
    container_name: ds41-cp2-d2
    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
      --enable-prefill-cp --cp-strategy interleave
      --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