I am running GPU instance on GKE when everything is deployed I make the request to the service Above mention error occur I followed all the step in mentioned in https://cloud.google.com/kubernetes-engine/docs/how-to/gpus#ubuntu This is my DockerFile

FROM nvidia/cuda:10.2-cudnn7-devel

# install nginx
# RUN apt-get update && apt-get install nginx vim -y --no-install-recommends
# RUN ln -sf /dev/stdout /var/log/nginx/access.log \
#     && ln -sf /dev/stderr /var/log/nginx/error.log

## Setup 

RUN mkdir -p /opt/app

RUN apt-get update -y && \
    apt-get install -y --no-install-recommends \
    python3-dev \
    python3-pip \
    python3-wheel \
    python3-setuptools && \
    rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*

RUN pip3 install --no-cache-dir -U install setuptools pip
RUN pip3 install --no-cache-dir cupy_cuda102==8.0.0rc1 scipy optuna

COPY requirements.txt start.sh run.py uwsgi.ini utils.py /opt/app/
COPY shading_characteristics /opt/app/shading_characteristics

WORKDIR /opt/app
RUN pip install -r requirements.txt
RUN pip install --upgrade 'sentry-sdk[flask]'
RUN pip install uwsgi -I --no-cache-dir

EXPOSE 5000

## Start the server, giving permissions for script
# COPY nginx.conf /etc/nginx
RUN chmod +x ./start.sh 
RUN chmod -R 777 /root
CMD ["./start.sh"]