# reward-seat — the fleet's scalar reward model, on esh-ml1 (RTX 2000E Ada, 16 GB).
#
# Moved here from fv-ml1's `vllm` stack on 2026-09-25 (Prime: utility seats off
# the Blackwells). Same model files (sha256-identical copy of fv-ml1's local AWQ
# output), same vLLM version and flags. Only the GPU and the host changed.
#
#   vllm-reward   Skywork-Reward-V2-Llama-3.1-8B, AWQ W4A16 (llm-compressor,
#                 score head kept full precision) → /classify   :8003
#
# vLLM, not TEI: TEI cannot serve a Llama sequence-classification head. That
# makes this the one vLLM seat on esh-ml1; embed/rerank are TEI
# (stacks/embed-rerank).
#
# Scores are SWAP-SENSITIVE: a different model or quant shifts the scale and
# every consumer threshold with it. /classify returns sigmoid probs by default;
# send "use_activation": false for the raw reward.
#
# Consumers reach it through the gateway passthrough `/scalar-judge` on
# ana-docker:4000 (stacks/litellm, pass_through_endpoints). Worldtree's Domari
# hardcodes an address instead (see README).
#
# Model files: /opt/aimodels/llm/Skywork-Reward-V2-Llama-3.1-8B-AWQ (local quant,
# not on HF Hub; the canonical copy also lives on fv-ml1 /tank/aimodels/llm).

name: reward-seat

services:
  vllm-reward:
    image: vllm/vllm-openai:${VLLM_VERSION}
    container_name: vllm-reward
    restart: unless-stopped
    ipc: host
    ports:
      - "${REWARD_PORT}:8000"
    volumes:
      - /opt/aimodels/llm:/local-models:ro
    environment:
      - VLLM_API_KEY=${API_KEY:-}
    command:
      - /local-models/Skywork-Reward-V2-Llama-3.1-8B-AWQ
      - --served-model-name
      - Skywork/Skywork-Reward-V2-Llama-3.1-8B-AWQ
      # config.json declares LlamaForSequenceClassification; the pooling
      # runner serves it as a single-label classifier.
      - --runner
      - pooling
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --gpu-memory-utilization
      - ${REWARD_GPU_MEM_UTIL}
      - --max-model-len
      - ${REWARD_MAX_MODEL_LEN}
      - --dtype
      - auto
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["0"]
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 240s
    labels:
      - homepage.group=AI - Eval & Retrieval
      - homepage.name=Reward — Skywork V2 8B (esh-ml1)
      - homepage.icon=mdi-scale-balance
      - homepage.description=Scalar reward classifier (/scalar-judge) via vLLM on esh-ml1
      - homepage.href=http://10.0.50.80:${REWARD_PORT}/docs