# mOrpheus — uncensored Orpheus TTS, permanent stack on irv-ml1.
#
# Two services:
#   vllm-morpheus (GPU, 3090, FP8) — serves the mOrpheus 3B LLM; emits Orpheus audio
#     tokens. Real-time: ~165 tok/s single-stream => RTF ~0.50 (2x real-time), measured.
#   morpheus-tts  (CPU) — SNAC-decodes those tokens to 24kHz WAV; the public /tts endpoint
#     (baddy voice + optional zero-shot cloning). Kept off the GPU to avoid contention.
#
# PLACEMENT / GOTCHAS (irv-ml1, INTERNAL RESEARCH — CC-BY-NC, do NOT expose externally):
#   - GPU = the 3090 (audio-zoo GPU, stabler); the A6000 is comfy's and spikes to ~41GB
#     without warning (it OOM'd two launch attempts). Pin by UUID via MORPHEUS_GPU_UUID.
#   - Image PINNED to vllm/vllm-openai:v0.23.0 — `latest` ships Blackwell-only kernels
#     (oink/aiter) that crash on Ampere import. Do NOT bump to latest on this Ampere box.
#   - bf16 REQUIRED, NOT FP8. FP8 (--quantization fp8) destroys audio-token generation on
#     this model — 0 valid SNAC frames even at greedy (quant-breaks-TTS). bf16 weights are
#     ~6.6GB; with --enforce-eager (no CUDA-graph capture) it fits the shared 3090 (~8GB
#     free after nothing else vLLM). util 0.32 (~7.7GB of the 24GB 3090).
#   All tunables in .env — edit that, not this file.

name: morpheus

services:
  vllm-morpheus:
    image: vllm/vllm-openai:v0.23.0
    container_name: vllm-morpheus
    restart: unless-stopped
    runtime: nvidia
    ipc: host
    environment:
      - NVIDIA_VISIBLE_DEVICES=${MORPHEUS_GPU_UUID:-GPU-12c15b3c-0827-0bab-b0cd-31aaa37a8e72}
      - CUDA_DEVICE_ORDER=PCI_BUS_ID
    volumes:
      - ${MORPHEUS_MODEL_DIR:-/home/lkraven/morpheus/models/mOrpheus}:/model:ro
    command:
      - /model
      - --served-model-name
      - morpheus
      - --dtype
      - bfloat16
      # NO --quantization: FP8 breaks audio-token generation on this model (see header).
      - --enforce-eager
      - --max-model-len
      - "${MORPHEUS_MAX_LEN:-4096}"
      - --gpu-memory-utilization
      - "${MORPHEUS_GPU_UTIL:-0.32}"
      - --max-num-seqs
      - "${MORPHEUS_MAX_SEQS:-8}"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 300s
    networks: [morpheus-net]

  morpheus-tts:
    build: ./tts
    image: morpheus-tts:local
    container_name: morpheus-tts
    restart: unless-stopped
    depends_on:
      vllm-morpheus:
        condition: service_healthy
    environment:
      - VLLM_URL=http://vllm-morpheus:8000/v1/completions
      - VLLM_MODEL=morpheus
      - SNAC_DEVICE=cpu
      - MORPHEUS_DEFAULT_VOICE=${MORPHEUS_DEFAULT_VOICE:-baddy}
      - MORPHEUS_VOICES=${MORPHEUS_VOICES:-baddy}
      - MORPHEUS_VOICES_DIR=/voices          # <name>.wav + <name>.txt => voice="<name>" clones it
      - MORPHEUS_MAX_LEN=${MORPHEUS_MAX_LEN:-4096}   # must match engine --max-model-len (max_tokens clamp)
    volumes:
      - ${MORPHEUS_MODEL_DIR:-/home/lkraven/morpheus/models/mOrpheus}:/model:ro
      - ${SNAC_DIR:-/home/lkraven/morpheus/models/snac_24khz}:/snac:ro
      - ${MORPHEUS_VOICES_DIR:-/home/lkraven/morpheus/voices}:/voices:ro
    ports:
      - "${MORPHEUS_TTS_PORT:-8299}:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    labels:
      - homepage.group=AI - Speech (TTS)
      - homepage.name=mOrpheus TTS
      - homepage.icon=mdi-account-voice
      - homepage.description=Uncensored Orpheus TTS (baddy + zero-shot clone), real-time, irv-ml1
      - homepage.href=http://10.100.79.3:${MORPHEUS_TTS_PORT:-8299}/docs
    networks: [morpheus-net]

networks:
  morpheus-net:
    name: morpheus-net