# ROCm (AMD GPU) overlay for Voicebox
#
# Usage:
#   docker compose -f docker-compose.yml -f docker-compose.rocm.yml up --build
#
# Prerequisites on the host:
#   1. ROCm drivers installed — https://rocm.docs.amd.com/projects/install-on-linux
#   2. Current user in the 'render' and 'video' groups:
#        sudo usermod -aG render,video $USER   (then log out/in)
#
# If the render/video GIDs on your host differ from the Ubuntu 22.04 defaults
# (render=992, video=44), export them before running compose so the build arg
# and group_add values both stay in sync automatically:
#   export RENDER_GID=$(getent group render | cut -d: -f3)
#   export VIDEO_GID=$(getent group video  | cut -d: -f3)
#   docker compose -f docker-compose.yml -f docker-compose.rocm.yml up --build
#
# ROCm version (ROCM_VERSION):
#   Default is 6.3 (supports RDNA1/2/3). For RDNA 4 (RX 9000 series) use 7.2:
#   export ROCM_VERSION=7.2
#   docker compose -f docker-compose.yml -f docker-compose.rocm.yml up --build

services:
  voicebox:
    build:
      context: .
      args:
        PYTORCH_VARIANT: rocm
        # These build args read from env vars so a single export covers both the
        # Dockerfile group creation and the runtime group_add below.
        RENDER_GID: ${RENDER_GID:-992}
        VIDEO_GID: ${VIDEO_GID:-44}
        ROCM_VERSION: ${ROCM_VERSION:-6.3}

    # Pass the AMD GPU device nodes into the container.
    # /dev/kfd  — ROCm compute interface (required for GPU inference)
    # /dev/dri  — DRM render nodes (required for display/memory access)
    devices:
      - /dev/kfd
      - /dev/dri

    # Grant access to the render and video groups so the non-root user
    # inside the container can open the GPU device nodes.
    # These reference the same env vars used in build.args above so a
    # single export keeps Dockerfile groups and runtime group_add in sync.
    group_add:
      - "${RENDER_GID:-992}"   # render
      - "${VIDEO_GID:-44}"     # video

    environment:
      # HSA_OVERRIDE_GFX_VERSION forces the ROCm runtime to treat the GPU as a
      # specific GFX version when auto-detection fails or the GPU is newer than
      # the ROCm release. app.py sets 10.3.0 (RDNA2) by default; override here
      # for your GPU family:
      #   RDNA4 / RX 9000 series:              12.0.0  (requires ROCM_VERSION=7.2)
      #   RDNA3 / RX 7000 series / Strix Halo: 11.0.0
      #   RDNA2 / RX 6000 series:              10.3.0
      #   RDNA1 / RX 5000 series:              10.1.0
      #   Vega / GCN5:                          9.0.0
      - HSA_OVERRIDE_GFX_VERSION=11.0.0

      # Tune the ROCm memory allocator to reduce fragmentation during
      # multi-engine inference (TTS + STT + LLM running concurrently).
      - PYTORCH_HIP_ALLOC_CONF=garbage_collection_threshold:0.8,max_split_size_mb:512