ollama      1110  0.0  0.0 2668044 43872 ?       Ssl   2025   8:26 /usr/local/bin/ollama serve
www-data  135407  0.0  0.0   2576   924 ?        S    03:09   0:00 sh -c cd /var/www/html/ai-engine && /var/www/html/ai-engine/env/bin/python3.11 llama3_text_image.py https://dashboard.feedspark.com/img/cricket.jpg 2>&1
www-data  135408  187  1.4 35017504 1939744 ?    Rl   03:09   0:08 /var/www/html/ai-engine/env/bin/python3.11 llama3_text_image.py https://dashboard.feedspark.com/img/cricket.jpg
www-data  135498  0.0  0.0   2576   924 ?        S    03:09   0:00 sh -c ps aux | grep llama
www-data  135500  0.0  0.0   3324  1508 ?        S    03:09   0:00 grep llama
root     1670839  0.1  0.8 11029620 1148172 pts/1 Sl+  2025 260:03 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