Not able to run via docker: nvidia-container-cli: initialization error: load library failed: libnvidia-ml.so.1:
#44
by khanfarhan10 - opened
docker run \
--rm \
--gpus all \
--network host \
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddlex-genai-vllm-server
Unable to find image 'ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddlex-genai-vllm-server:latest' locally
latest: Pulling from paddlepaddle/paddlex-genai-vllm-server
e335b9092447: Pull complete
32b550be6cb6: Pull complete
35af2a7690f2: Pull complete
7576b00d9bb1: Pull complete
ff1cff00b1dd: Pull complete
57e75b8db17c: Pull complete
e844e4b3e270: Pull complete
4ffff3de336e: Pull complete
c336539cd2cd: Pull complete
eee8a02d0a37: Pull complete
Digest: sha256:da9361a576ad39f85117431671400ab3acfbc9072b9cd1256a98a17ea9666872
Status: Downloaded newer image for ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddlex-genai-vllm-server:latest
docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running prestart hook #0: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy'
nvidia-container-cli: initialization error: load library failed: libnvidia-ml.so.1: cannot open shared object file: no such file or directory: unknown
Do you have a GPU driver locally?
I had this issue.
Solution was to add the flag : --runtime nvidia
But I have personnally an other issue after that which is posted here : https://huggingface.co/PaddlePaddle/PaddleOCR-VL/discussions/51