sglang/deploy/b300-ds41/dockerserve-3cp2-pd.yml

# 3x cp2-P + 1x dp2-D PD 分离 + L3 mooncake 互联缓存 + engram host table
# 2026-09-23 实验；基线见 archive-20260923/ 与 D:\B300\experiments\3cp2-pd\baseline-20260923.md
# GPU: P1=0,1 P2=2,3 P3=4,5 D=6,7
# 端口: P1=30000 P2=30010 P3=30020 D=30001 router=30002
# bootstrap: P1=8998 P2=8999 P3=9000 D=9001
x-sglang-common: &sglang-common
  image: ymkymx/sglang:dsv41-pd-visioncp-db7d2cb7d-fix
  shm_size: "32gb"
  ipc: host
  pid: host
  privileged: true
  network_mode: host
  volumes:
    - /data:/data
    - /data/ymk/cache/sglang:/root/.cache/sglang
  deploy:
    resources:
      reservations:
        devices:
          - driver: nvidia
            count: all
            capabilities: [gpu]

x-p-environment: &p-environment
  SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE: "1"
  SGLANG_RAGGED_VERIFY_MODE: static
  MC_INTRANODE_NVLINK: "true"
  MC_INTRA_NVLINK: "true"
  SGLANG_MOONCAKE_SEND_AUX_TCP: "1"
  SGLANG_HICACHE_MOONCAKE_CONFIG_PATH: /data/ymk/ds41/mooncake-store.json
  SGLANG_DISAGGREGATION_QUEUE_SIZE: "16"
  SGLANG_DISAGGREGATION_THREAD_POOL_SIZE: "32"

services:
  p1:
    <<: *sglang-common
    container_name: ds41-cp2-p1
    environment:
      <<: *p-environment
      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
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
      --disaggregation-bootstrap-port 8998

  p2:
    <<: *sglang-common
    container_name: ds41-cp2-p2
    environment:
      <<: *p-environment
      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
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
      --disaggregation-bootstrap-port 8999

  p3:
    <<: *sglang-common
    container_name: ds41-cp2-p3
    environment:
      <<: *p-environment
      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
      --disaggregation-mode prefill
      --disaggregation-transfer-backend mooncake
      --disaggregation-bootstrap-port 9000

  d:
    <<: *sglang-common
    container_name: ds41-cp2-d
    environment:
      SGLANG_ENABLE_DSV41_ENGRAM_HOST_TABLE: "1"
      SGLANG_RAGGED_VERIFY_MODE: static
      MC_INTRANODE_NVLINK: "true"
      MC_INTRA_NVLINK: "true"
      SGLANG_MOONCAKE_SEND_AUX_TCP: "1"
      SGLANG_DISAGGREGATION_QUEUE_SIZE: "16"
      SGLANG_DISAGGREGATION_THREAD_POOL_SIZE: "32"
      CUDA_VISIBLE_DEVICES: "6,7"
    command: >
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 2 --ep-size 2 --dp-size 2
      --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 30001
      --enable-cache-report --enable-metrics
      --speculative-algorithm DSPARK --speculative-dspark-block-size 5
      --disaggregation-mode decode
      --disaggregation-transfer-backend mooncake
      --disaggregation-bootstrap-port 9001