tftsr_ai/templates/ollama/warmup.sh.j2

#!/bin/bash
# Ollama model warm-up script
# Sends a 1-token generation to each slot model to pin them in RAM

set -e

OLLAMA_URL="http://localhost:11434"
API_KEY="{{ ollama_api_key }}"

warmup_model() {
    local model="$1"
    echo "[warmup] Loading model: $model"
    curl -sf -X POST "${OLLAMA_URL}/api/generate" \
        -H "Authorization: Bearer ${API_KEY}" \
        -H "Content-Type: application/json" \
        -d "{\"model\":\"${model}\",\"prompt\":\"Hi\",\"stream\":false,\"options\":{\"num_predict\":1}}" \
        > /dev/null || echo "[warmup] Warning: failed to warm up ${model}"
    echo "[warmup] Done: $model"
}

warmup_model "{{ slot1_model }}"
warmup_model "{{ slot2_model }}"
warmup_model "{{ slot3_model }}"
warmup_model "{{ slot4_model }}"

echo "[warmup] All models warmed up."