services:
  h3-hot-runtime:
    profiles: ["h3"]
    image: h3-blackwell-runtime:dev
    container_name: h3-hot-runtime
    restart: unless-stopped
    gpus: all
    volumes:
      - /home/daniel/aeon-spark-test/h3/comfy-models/diffusion_models:/models:ro
      - /home/daniel/aeon-spark-test/h3/comfy-models/text_encoders:/text-encoders:ro
      - /home/daniel/aeon-spark-test/h3/comfy-models/vae:/vae:ro
      - /home/daniel/aeon-spark-test/h3/h3-blackwell-runtime/artifacts:/artifacts:ro
      - /home/daniel/StoryStudioAssets/H3-output:/output
    ports:
      - "8001:8000"
    environment:
      H3_DISABLE_MMAP: "1"
      H3_NVFP4_SCALE_BACKEND: "vortex"
      H3_NVFP4_SCALE_VERSION: "1"
      H3_FUSED_ELEMENTWISE: "1"
      H3_NVFP4_MODULATE_FUSION: "1"
      H3_NVFP4_SWIGLU_FUSION: "1"
      H3_SAGE_QKV_LAYOUT: "strided_nhd"
      H3_SOL_QKV_LAYOUT: "native"
    command: ["python", "/opt/h3-blackwell-runtime/tools/serve_hot_runtime.py", "--host", "0.0.0.0", "--port", "8000", "--attention", "sage2", "--warmup"]

  qwen38-vllm:
    profiles: ["qwen"]
    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

  flux2-klein-comfy:
    profiles: ["flux"]
    image: ghcr.io/aeon-7/comfyui-aeon-spark:slim
    container_name: flux2-klein-comfy
    restart: unless-stopped
    gpus: all
    ipc: host
    shm_size: 16g
    volumes:
      - /home/daniel/aeon-spark-test/workspace:/workspace/ComfyUI:rw
      - /home/daniel/StoryStudioAssets/H3-output:/workspace/ComfyUI/output:rw
      - /home/daniel/aeon-spark-test/extra_model_paths.yaml:/opt/ComfyUI/extra_model_paths.yaml:ro
      - /home/daniel/comfy-data/models:/shared-models:ro
    ports:
      - "8192:8188"