# erp-seat — the ERP-tune seat on ana-ml2 GPU1: NVFP4A16 quant of the latest gated ERP LoRA merge
# (run 7 = jenerallee78 ARA-abliterated Gemma-4-26B-A4B + R47 SFT + the opening-split slot), served under its TRUE name.
# Routing aliases (e.g. LiteLLM `trial`) are the operator's call and live in the gateway, not here.
#
# Serve recipe copied from stacks/gemma4-charrp (same architecture + quant format, proven on this
# box): gemma4 tool + reasoning parsers, enable_thinking pinned false, model's own stock template.
# GPU1 is SHARED (charrp-MoE moved? no — scriberr, embed, rerank, coder, reward live there):
# ~47 GiB was free on 2026-09-08; 0.35 x 97.9 GiB = 34 GiB keeps ~13 GiB of real margin.
# Quant pipeline: services/erp-seat-quant/. Tunables in .env.

name: erp-seat

services:
  vllm-erp-seat:
    image: ${ERP_IMAGE:-vllm/vllm-openai:nightly-311b3513af33bc29b4acb2fde2e9313e5e9966a0}
    container_name: ${ERP_CONTAINER:-vllm-erp-seat}
    restart: unless-stopped
    ipc: host
    ports:
      - "${ERP_PORT:-8021}:8000"
    volumes:
      - /tank/aimodels:/tank/aimodels
    environment:
      - VLLM_API_KEY=${API_KEY:-}
    command:
      - ${ERP_MODEL:-/tank/aimodels/erp-tune-v7-nvfp4a16}
      - --quantization
      - compressed-tensors
      - --served-model-name
      - ${ERP_SERVED_NAME:-erp-tune-v7-nvfp4a16}
      - --tool-call-parser
      - gemma4
      - --enable-auto-tool-choice
      # --reasoning-parser gemma4 + the enable_thinking pin are BOTH required (measured 2026-09-08):
      # without them the post-tool-response turn leaks a literal "<|channel>thought\n<channel|>"
      # prefix into content (3/3), exactly as stacks/gemma4-charrp/README.md warns. They do NOT
      # fix forced (named) tool_choice — that failure is independent of the reasoning parser
      # (measured 1/9 with it, 3/9 without): the model free-writes Gemma native call syntax
      # instead of grammar-constrained JSON. See README for the forced-tool_choice status.
      - --reasoning-parser
      - gemma4
      - --default-chat-template-kwargs
      - '{"enable_thinking": false}'
      # tool_choice:"none" trap (measured 2026-09-08): without this flag vLLM still renders the
      # tools into the prompt, the model emits a tool call anyway, and because tool parsing is
      # off for tool_choice=none the reply comes back with content=null AND tool_calls=null —
      # an empty turn. The flag drops the tools from the prompt so the model answers in prose.
      - --exclude-tools-when-tool-choice-none
      - --chat-template
      - ${ERP_CHAT_TEMPLATE:-/tank/aimodels/erp-tune-v7-nvfp4a16/chat_template.jinja}
      - --max-model-len
      - "${ERP_MAX_MODEL_LEN:-32768}"
      - --max-num-seqs
      - "${ERP_MAX_NUM_SEQS:-8}"
      - --gpu-memory-utilization
      - "${ERP_GPU_MEM_UTIL:-0.35}"
      - --kv-cache-dtype
      - fp8
      - --trust-remote-code
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids:
                - "${ERP_GPU_ID:-1}"
              capabilities:
                - gpu
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 600s
    networks:
      - tnet
    labels:
      - homepage.group=AI - Inference
      - homepage.name=erp-tune-v7 (Gemma-4 26B-A4B ARA, NVFP4A16)
      - homepage.icon=mdi-fire
      - homepage.description=ERP-seat run-7 LoRA merge on the jenerallee78 abliteration, NVFP4A16 MoE (ana-ml2 GPU1)
      - homepage.href=http://10.250.50.54:${ERP_PORT:-8021}/docs

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