# tei-bakeoff — Hugging Face Text Embeddings Inference (TEI) serving the SAME two
# models as stacks/embed-rerank (vLLM), side by side on esh-ml1, so the two
# engines can be compared on identical hardware. Prime, 2026-09-25: "run the
# TEI bake-off". Not wired into the gateway. Temporary: either this becomes the
# embed-rerank stack or it is torn down.
#
#   tei-embed    Qwen/Qwen3-Embedding-0.6B  → /v1/embeddings, /embed   :8081
#   tei-rerank   BAAI/bge-reranker-v2-m3    → /rerank                  :8083
#
# 89-* = the Ada Lovelace (sm_89) build. Pinned to an exact release.
# TEI on CUDA offers float16/float32 only (no bfloat16), while vLLM serves
# Qwen3-Embedding in bf16 — the parity measurement is what decides whether
# that matters.
# (--max-batch-tokens 32768 was tried on tei-embed: whole-novel time unchanged,
# 39.2–40.4 s vs 39.9–40.3 s, so it stays at the default.)
# --max-client-batch-size 128: the default is 32; vLLM has no such cap and the
# bake-off sends 64 per request.
# Separate HF cache from vLLM's, so neither engine can disturb the other's files.

name: tei-bakeoff

services:
  tei-embed:
    image: ghcr.io/huggingface/text-embeddings-inference:89-1.9.4
    container_name: tei-embed
    restart: unless-stopped
    ports:
      - "8081:80"
    volumes:
      - /opt/aimodels/tei-cache:/data
    command:
      - --model-id
      - Qwen/Qwen3-Embedding-0.6B
      - --served-model-name
      - Qwen/Qwen3-Embedding-0.6B
      - --dtype
      - float16
      - --max-client-batch-size
      - "128"
      # FAIL-CLOSED on over-length input (Dvalin review 2026-09-25; measured:
      # TEI's default silently cut a ~40k-token input to 16,384 and returned
      # 200, where vLLM returns 400). Truncation off requires max-batch-tokens
      # >= the model's max input (Qwen3-Embedding: 32,768) or TEI refuses to start.
      - --auto-truncate
      - "false"
      - --max-batch-tokens
      - "32768"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["0"]
              capabilities: [gpu]

  tei-rerank:
    image: ghcr.io/huggingface/text-embeddings-inference:89-1.9.4
    container_name: tei-rerank
    restart: unless-stopped
    ports:
      - "8083:80"
    volumes:
      - /opt/aimodels/tei-cache:/data
    command:
      - --model-id
      - BAAI/bge-reranker-v2-m3
      - --dtype
      - float16
      - --max-client-batch-size
      - "128"
      # Fail-closed, as tei-embed. bge-reranker-v2-m3 max input (8,192) fits the
      # default max-batch-tokens (16,384).
      - --auto-truncate
      - "false"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["0"]
              capabilities: [gpu]