# start server with 3 parallel slots
./bin/llama-server -m ../models/qwen2.5-32b-coder-instruct/ggml-model-q8_0.gguf -ngl 99 -fa --port 8033 -c 0 -np 3

# generation task with small prompt
curl --request POST --url http://localhost:8033/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer no-key" -d "$(jq -n '{ messages: [{ role: "system", content: "You are a helpful assistant." }, { role: "user", content: "Write quick sort in c++." }], "stream": true }')"

# task with a large prompt
curl --request POST --url http://127.0.0.1:8033/completion --header "Content-Type: application/json" --data '{"prompt": "'"$(printf 'hello %.0s' $(seq 1 8149))"'. I believe the meaning of life is","n_predict": 64, "cache_prompt": true}' | jq