# lfm-vl-seat — LiquidAI LFM2.5-VL-3B (vision-language) on nh3-ml1 (CT 109 on
# nh3-pve, RTX 2000E Ada 16 GB), llama.cpp server. Utility seat for brokkr's
# dataset foundry (image understanding), operator-approved 2026-09-26 (relayed
# by brokkr-smithy-dev).
#
#   llama-server  LFM2.5-VL-3B Q5_K_M + mmproj Q8_0 → /v1/chat/completions
#                 (OpenAI, with image_url content parts)                 :8030
#
# ⚠ --mmproj is REQUIRED for image input; without it the model is text-only and
# says nothing about it.
# Batch work, not latency-critical: this card decodes ~5x slower than an fv-ml1
# Blackwell (servers/nh3-ml1/README.md), which is fine for a foundry.
#
# Files (not in git): /opt/aimodels/gguf/lfm25-vl-3b/ from
# LiquidAI/LFM2.5-VL-3B-GGUF @ 6f730e9a2c45.
name: lfm-vl-seat
services:
  llama-server:
    image: ${LLAMACPP_IMAGE}
    container_name: lfm-vl
    restart: unless-stopped
    ports:
      - "${VL_PORT}:8080"
    volumes:
      - /opt/aimodels/gguf/lfm25-vl-3b:/models:ro
    command:
      - -m
      - /models/${VL_MODEL_FILE}
      - --mmproj
      - /models/${VL_MMPROJ_FILE}
      - --alias
      - ${VL_ALIAS}
      - --host
      - 0.0.0.0
      - --port
      - "8080"
      - -ngl
      - "999"
      - -c
      - "${VL_CTX}"
      - -np
      - "${VL_PARALLEL}"
      - --jinja
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["0"]
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-fsS", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 120s
    labels:
      - homepage.group=AI - Eval & Retrieval
      - homepage.name=VL — LFM2.5-VL-3B (llama.cpp, nh3-ml1)
      - homepage.icon=mdi-image-search
      - homepage.description=Image understanding for the dataset foundry (gateway lfm25-vl-3b)
      - homepage.href=http://10.100.50.80:${VL_PORT}