services:
  qwen38-vllm:
    image: ghcr.io/aeon-7/aeon-vllm-ultimate:latest
    container_name: qwen38-vllm
    restart: unless-stopped
    gpus: all
    ipc: host
    shm_size: 16g
    network_mode: host
    volumes:
      - /home/daniel/aeon-spark-test/h3/models/Qwen3.8-27B-NVFP4:/model:ro
      - /home/daniel/aeon-spark-test/h3/vllm-cache:/root/.cache/vllm
    entrypoint: ["vllm"]
    command:
      - serve
      - /model
      - --served-model-name
      - qwen38
      - --host
      - 0.0.0.0
      - --port
      - "8002"
      - --tensor-parallel-size
      - "1"
      - --gpu-memory-utilization
      - "0.45"
      - --max-model-len
      - "262144"
      - --max-num-seqs
      - "4"
      - --max-num-batched-tokens
      - "8192"
      - --enable-chunked-prefill
      - --enable-prefix-caching
      - --kv-cache-dtype
      - fp8_e4m3
      - --reasoning-parser
      - qwen3
      - --tool-call-parser
      - qwen3_xml
      - --enable-auto-tool-choice
      - --distributed-executor-backend
      - mp
      - --speculative-config
      - '{"method":"mtp","num_speculative_tokens":5}'
      - --trust-remote-code