vllm serve Qwen/Qwen2.5-7B-Instruct --host 127.0.0.1 --port 8000 --max-num-seqs 4 &
moochy --home /var/lib/moochy keys add local --base-url http://127.0.0.1:8000 \
  --model local/qwen2.5-7b=Qwen/Qwen2.5-7B-Instruct
moochy --home /var/lib/moochy config set slots_max 4