| 12345678910111213141516171819202122232425262728 |
- #!/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 "{{ model_selection.slot1_general }}"
- warmup_model "{{ model_selection.slot2_general }}"
- {% if model_selection.slot5_general_rotate | default('') | length > 0
- and model_selection.slot5_general_rotate | default('none') != 'none' %}
- warmup_model "{{ model_selection.slot5_general_rotate }}"
- {% endif %}
- echo "[warmup] All Node 1 general models warmed up."
|
