services:
  qwen38-flash-next:
    build: .
    image: haloq38flash:latest
    container_name: qwen38-flash-next
    devices:
      - /dev/dri
    group_add:
      - video
      - render
    security_opt:
      - seccomp=unconfined
    volumes:
      - /mnt/ssd2/models/qwen38-flash-next:/models:ro
    ports:
      - "8080:8080"
    environment:
      - LD_LIBRARY_PATH=/app
    # the image CMD is bare (/app/llama-server) — pass the model + flags:
    command: >-
      -m /models/Qwen3.8-Flash-Next-IQ4_XS-PLE.gguf
      -ngl 999 -fa on -ctk q8_0 -ctv q8_0
      -c 32768 -ub 2048 -t 4 --jinja
    # for mtp speculative decoding:
    # command: >-
    #   -m /models/Qwen3.8-Flash-Next-IQ4_XS-PLE.gguf
    #   -md /models/mtp-Qwen3.8-Flash-Next-Q8_0.gguf
    #   --spec-type draft-mtp --spec-draft-n-max 6 --spec-draft-p-min 0.75
    #   -ngl 999 -fa on -ctk q8_0 -ctv q8_0 -c 32768 -ub 2048 -t 4 --jinja