docker run --rm --gpus "device=0" --name "mistral-llm0" -e CUDA_VISIBLE_DEVICES=0 -p 8000:8000 -v /opt/models/mistral:/models -t mistral-llm:cu122-avx
#docker run --rm --gpus all -p 8000:8000 -v /opt/models/mistral:/models -t mistral-llm:cu122-avx