# gemma4-trainee-bench — BF16 abliterated trainee base, served for benchmarking.
#
# EPHEMERAL BY DESIGN. This is not a production seat. It exists so the trainee
# base can be measured on the same battery as the served char-rp seat, and it
# takes GPU0 to itself while it runs.
#
# ⚠ IT CANNOT COEXIST WITH `vllm-gen`. The weights are BF16 — 48.07 GiB of a
# 94.97 GiB card — and gen actually holds ~45.6 GiB. 48.07 + 45.6 = 93.7 GiB
# before a single byte of KV cache, activations, CUDA graphs or non-torch
# overhead. Running this means gen is stopped, and gen coming back means this
# is stopped. There is no arrangement where both are up.
#
# ⚠ NO `--quantization` FLAG, AND THAT IS THE POINT.
# The production gemma4-charrp compose hardcodes `--quantization
# compressed-tensors` because it serves an NVFP4 build. Pointing that stack at
# these BF16 weights crash-loops immediately:
#     TypeError: CompressedTensorsConfig.__init__() missing 3 required
#     positional arguments: 'target_scheme_map', 'ignore', 'quant_format'
# vLLM tries to read a quantization config out of a checkpoint that has none.
# 35 restarts before it was caught. Hence a separate stack rather than another
# variable on the production one.
#
# SAME PORT AND SAME SERVED-MODEL-NAMES AS char-rp, deliberately: brokkr's
# battery targets the `char-rp` / `char-rp-reasoning` gateway aliases, so
# serving under those names means their harness needs no edit and the numbers
# are directly comparable to the runs already recorded. Only one of this stack
# and gemma4-charrp can be up at a time — both bind :8016.
#
# Tunables in .env.

name: gemma4-trainee-bench

services:
  vllm-gemma4-trainee-bench:
    image: ${BENCH_IMAGE:-vllm/vllm-openai:v0.26.0}
    container_name: ${BENCH_CONTAINER:-vllm-gemma4-trainee-bench}
    # `no`, not unless-stopped. A bench seat that resurrects itself after the
    # window closes would silently hold 48 GiB and block gen's restore.
    restart: "no"
    ipc: host
    ports:
      - "${BENCH_PORT:-8016}:8000"
    volumes:
      - /tank/aimodels:/tank/aimodels
    environment:
      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
      - VLLM_API_KEY=${API_KEY:-}
    command:
      - ${BENCH_MODEL:-/tank/aimodels/gemma4-26b-a4b-it-heretic-bf16}
      - --served-model-name
      - char-rp
      - char-rp-thinking
      # Architecture-level Gemma-4 flags, identical to the production seat —
      # see stacks/gemma4-charrp/README.md for why each is load-bearing.
      - --tool-call-parser
      - gemma4
      - --enable-auto-tool-choice
      - --reasoning-parser
      - gemma4
      - --default-chat-template-kwargs
      - '{"enable_thinking": false}'
      # ⚠ UPSTREAM TEMPLATE, NOT THE ONE THIS CHECKPOINT SHIPS.
      # Every third-party Gemma-4 derivative carries a stale template: this
      # abliterated build ships a 365-line file, the stock upstream is 390
      # lines. Benching through a different template than production serves
      # would make the comparison meaningless — the same reason the production
      # seat pins it.
      - --chat-template
      - ${BENCH_CHAT_TEMPLATE:-/tank/aimodels/gemma4-26b-a4b-it-nvfp4/chat_template.jinja}
      - --max-model-len
      - "${BENCH_MAX_MODEL_LEN:-262144}"
      - --max-num-seqs
      - "${BENCH_MAX_NUM_SEQS:-32}"
      # Card to itself. 0.92 leaves ~7 GiB of real headroom on top of 48 GiB of
      # weights — deliberately not 0.95, after a seat crash-looped this
      # afternoon on 0.6 GiB of margin.
      - --gpu-memory-utilization
      - "${BENCH_GPU_MEM_UTIL:-0.92}"
      - --kv-cache-dtype
      - fp8
      - --trust-remote-code
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids:
                - "${BENCH_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
    # No homepage labels. This is a transient bench seat; giving it a dashboard
    # card would leave a permanently-offline entry once the window closes.

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