# qwopus3.5-122b — OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destilled-abliterated-NVFP4
# on fv-ml1 GPU 0, REPLACING the bjk110 text-only qwen3.5-122b as the `gen` model
# (operator 2026-06-19: "already ablated, already quanted, vision tower intact").
#
# Qwen3.5-122B-A10B MoE, Kimi-K2.6-distilled + abliterated, NVFP4 — and crucially
# VISION-INTACT (Qwen3_5MoeForConditionalGeneration + vision_config). So it serves as
# plain MULTIMODAL (no text-only patch, unlike the bjk110 checkpoint which had its
# vision weights stripped). vLLM carries the arch natively.
#
# Served under --served-model-name qwen3.5-122-a10b so the existing litellm records
# (gen / gen-reasoning / qwen3.5-122-a10b[-reasoning] / qwen-large[-reasoning]) route
# here UNCHANGED — the operator's "replace those records with this model". The thinking
# split (chat_template_kwargs.enable_thinking) + tool-calling (qwen3_coder — the
# OpenYourMind card's specified parser for this checkpoint's XML tool calls).
#
# REVERT: down this; the bjk110 qwen3.5-122b stack is still staged.
# Tunables in .env.

name: qwopus3.5-122b

services:
  vllm-qwopus35-122b:
    image: ${QWOPUS_IMAGE:-vllm/vllm-openai:latest}
    container_name: ${QWOPUS_CONTAINER_NAME:-vllm-qwopus35-122b}
    restart: unless-stopped
    ipc: host
    ports:
      - "${QWOPUS_PORT:-8013}:8000"
    volumes:
      - /tank/aimodels/huggingface:/hfcache
      - /tank/aimodels/qwopus3.5-122b-nvfp4:/model:ro
    environment:
      - HF_HOME=/hfcache
      - HF_HUB_CACHE=/hfcache/hub
      - VLLM_API_KEY=${API_KEY:-}
      # Reclaims PyTorch's reserved-but-unallocated fragmentation (4.2GB was stranded at
      # util 0.96, starving the FusedMoE workspace → OOM by 0.1GB). Lets the 3.09GB MoE
      # workspace allocate cleanly. Same knob the bjk110 qwen3.5-122b stack ran.
      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
    command:
      - /model
      - --served-model-name
      - ${QWOPUS_SERVED_NAME:-qwen3.5-122-a10b}
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --gpu-memory-utilization
      - ${QWOPUS_GPU_MEM_UTIL:-0.92}
      - --max-model-len
      - ${QWOPUS_MAX_MODEL_LEN:-131072}
      - --max-num-seqs
      - ${QWOPUS_MAX_NUM_SEQS:-8}
      - --max-num-batched-tokens
      - "32768"
      - --trust-remote-code
      - --dtype
      - auto
      - --enable-prefix-caching
      - --enable-chunked-prefill
      # FULL 256K context on the STABLE image. fp8 KV (near-lossless) measured an 11.8GB
      # pool = 934,600 tokens = 3.5x concurrency at the full 262144 window. CUDA graphs ON
      # (no --enforce-eager) for decode tok/s. BINDING LIMIT = the FusedMoE transient
      # workspace (3.09GB, allocated OUTSIDE vLLM's budget into free VRAM): at util 0.96
      # only 2.99GB was free → OOM by 0.1GB, worsened by 4.2GB PyTorch fragmentation.
      # FIX = expandable_segments (env above, reclaims the fragmentation) + util 0.95 for
      # margin. The card can't go to 0 free — this workspace is the floor. video kept
      # ENABLED (operator wants it; banked at util 0.95 with headroom) — the video encoder
      # profiling eats into the budget so KV concurrency drops some, but stays well above 2x.
      - --kv-cache-dtype
      - ${QWOPUS_KV_CACHE_DTYPE:-fp8}
      - --limit-mm-per-prompt
      - '{"image": 2, "video": 1}'
      # reasoning split + tool-calling. The OpenYourMind card specifies qwen3_coder
      # as the tool-call parser for this checkpoint (Qwen3.5 XML tool-call format).
      - --reasoning-parser
      - qwen3
      - --enable-auto-tool-choice
      - --tool-call-parser
      - qwen3_coder
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids:
                - "${QWOPUS_GPU_ID:-0}"
              capabilities:
                - gpu
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 900s
    networks:
      - tnet
    labels:
      - homepage.group=AI - Dormant
      - homepage.name=Qwopus3.5-122B-A10B (abliterated NVFP4, vision)
      - homepage.icon=mdi-creation
      - homepage.description=Kimi-distilled abliterated Qwen3.5-122B-A10B NVFP4, vision-intact, the `gen` model (fv-ml1 GPU 0)
      - homepage.href=http://10.251.50.54:${QWOPUS_PORT:-8013}/docs

networks:
  tnet:
    name: traefik-net
    external: true