# TRANSIENT h2o-lightning-4b eval seat on fv-ml1 GPU 3 (GPU 3 is for transient work only).
# Round 1, 2026-10-12 1300-1319: albok-dev validated Nemi's judge on h2o before the GPU 1 cutover (Prime via brokkr).
# Round 2, from 2026-10-12 ~1430 (Prime 1420, via albok-dev): "I'd like to understand why h2o failed, so stand it up
#   on gpu3 and refit it and let's get an understanding." albok-dev investigates the 154 texts h2o alone called adult
#   and re-fits the judge. Two fronts over ONE vLLM:
#     :8034 front          the shim's yes/no floor ON (0.801), exactly as the live cutover ran; /health model stamp
#                          h2o-lightning-4b@b43f759b..., identical to the cutover's
#     :8035 front-nofloor  SHIM_NOUL_FLOOR=0 (floor OFF, brokkr's lever); stamp h2o-lightning-4b+noul-floor-0@b43f759b...
#   Each /health also reports backend.noul_floor {value, source}. NO load tests or other traffic while albok-dev's
#   runs are in (they name start/end on thread 01M4S026GWS354WZGXZ5E34F31). INC keeps :8033 on GPU 1, untouched.
# Serving exactly as benched (docs/pfi/decision-sweep-followon-bench-2026-10-12.md, Amendment 1): stock vLLM 0.30.0
# + the vendor's unmodified shim + the admission front (services/h2o-decision-front, copied into conf/front).
# Weights: /tank/aimodels/h2o-lightning-4b-b43f759b (hashes match HF at b43f759b; see the stack README).
# Inline images only (Prime 2026-10-12): LIGHTNING_IMAGE_URLS=off on both fronts + vLLM --allowed-media-domains.
name: h2o-eval
services:
  vllm:
    image: vllm/vllm-openai:v0.30.0
    container_name: h2o-eval-vllm
    restart: unless-stopped
    ports:
      - "127.0.0.1:18199:8000"
    environment:
      VLLM_USE_FLASHINFER_SAMPLER: "0"
    volumes:
      - /tank/aimodels/h2o-lightning-4b-b43f759b:/model:ro
      - h2o-eval-vllm-cache:/root/.cache/vllm
    command: ["--model", "/model", "--served-model-name", "h2oai/h2o-lightning-4b",
              "--max-model-len", "40960", "--max-num-seqs", "16", "--gpu-memory-utilization", "0.1506",
              "--limit-mm-per-prompt", "{\"image\": 4, \"video\": 0}",
              "--mm-processor-kwargs", "{\"max_pixels\": 1605632}",
              "--allowed-media-domains", "media.invalid"]
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["3"]
              capabilities: [gpu]
  front:
    image: python:3.12-slim
    container_name: h2o-eval-front
    restart: unless-stopped
    network_mode: host
    depends_on: [vllm]
    env_file: .env
    environment:
      SHIM_VLLM: http://127.0.0.1:18199
      SHIM_PORT: "18191"
      SHIM_NOUL_FLOOR: "0.801"
      LIGHTNING_IMAGE_URLS: "off"   # Prime 2026-10-12: inline images only, the seat never fetches an image URL
      FRONT_SHIM: http://127.0.0.1:18191
      FRONT_VLLM: http://127.0.0.1:18199
      FRONT_BIND: 0.0.0.0
      FRONT_PORT: "8034"
      FRONT_CAP: "32000"
      FRONT_SHIM_FILE: /model/h2o_lightning_shim.py
      FRONT_SERVE_CONFIG: /model/serve_config.json
      FRONT_MODEL_REVISION: b43f759b6385d21182f87c3829931ec3d4dfa98a
    volumes:
      - /tank/aimodels/h2o-lightning-4b-b43f759b:/model:ro
      - /opt/docker/conf/h2o-eval/front:/front:ro
    command: ["bash", "/front/run.sh"]
  front-nofloor:
    image: python:3.12-slim
    container_name: h2o-eval-front-nofloor
    restart: unless-stopped
    network_mode: host
    depends_on: [vllm]
    env_file: .env
    environment:
      SHIM_VLLM: http://127.0.0.1:18199
      SHIM_PORT: "18192"
      SHIM_NOUL_FLOOR: "0"           # the floor OFF (the shim: 0 turns it off)
      LIGHTNING_IMAGE_URLS: "off"   # Prime 2026-10-12: inline images only, the seat never fetches an image URL
      FRONT_SHIM: http://127.0.0.1:18192
      FRONT_VLLM: http://127.0.0.1:18199
      FRONT_BIND: 0.0.0.0
      FRONT_PORT: "8035"
      FRONT_CAP: "32000"
      FRONT_SHIM_FILE: /model/h2o_lightning_shim.py
      FRONT_SERVE_CONFIG: /model/serve_config.json
      FRONT_MODEL_NAME: h2o-lightning-4b+noul-floor-0   # a distinct judge stamp
      FRONT_MODEL_REVISION: b43f759b6385d21182f87c3829931ec3d4dfa98a
    volumes:
      - /tank/aimodels/h2o-lightning-4b-b43f759b:/model:ro
      - /opt/docker/conf/h2o-eval/front:/front:ro
    command: ["bash", "/front/run.sh"]
volumes:
  h2o-eval-vllm-cache: