services:
  sglang:
    image: ymkymx/sglang:dsv41-pd-ddf520763-local-20260923-0536
    container_name: ds41-cpdspark-l3-a
    shm_size: "32gb"
    ipc: host
    privileged: true
    network_mode: host
    environment:
      - CUDA_VISIBLE_DEVICES=0,1,2,3
      - 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=400gb
    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 4 --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto --tool-call-parser auto
      --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-prefill-cp --cp-strategy interleave
      --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
      --json-model-override-args '{"vision_n_layers": 0}'