ollama      1110  0.0  0.0 2668044 43420 ?       Ssl   2025   8:25 /usr/local/bin/ollama serve
www-data   21660  0.0  0.0   2576   928 ?        S    16:13   0:00 sh -c ps aux | grep llama
www-data   21662  0.0  0.0   3324  1524 ?        S    16:13   0:00 grep llama
root     1670839  0.1  0.8 11029620 1148172 pts/1 Sl+  2025 259:27 python3 -m vllm.entrypoints.openai.api_server --gpu-memory-utilization 0.95 --model=meta-llama/Llama-3.2-11B-Vision-Instruct --tokenizer=meta-llama/Llama-3.2-11B-Vision-Instruct --download-dir=/var/www/.cache/huggingface/hub --dtype=bfloat16 --host=77.68.79.111 --port=5000 --max-model-len=8192 --quantization=fp8 --enforce_eager --max_num_seqs=8 --no-enable_chunked-prefill