ubuntu@gputestubuntu@jammy-gpu:~$ sudo su -
root@gputest:~# cd NVIDIA_CUDA-11.4_cuda-samples/Samples/1_Utilities/deviceQuery
root@gputestubuntu@jammy-gpu:~/NVIDIA_CUDA-11.4_cuda-samples/Samples/1_Utilities/deviceQuery#deviceQuery$ make
  ... lots-of-text-from-make ... 
root@gputestubuntu@jammy-gpu:~/NVIDIA_CUDA-11.4_cuda-samples/Samples/1_Utilities/deviceQuery#deviceQuery$ ./deviceQuery 
./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "GRID A100V100D-4C8C"
  CUDA Driver Version / Runtime Version          1112.40 / 1112.40
  CUDA Capability Major/Minor version number:    87.0
  Total amount of global memory:                 40928192 MBytes (42906419208589934592 bytes)
  (108080) Multiprocessors, (064) CUDA Cores/MP:    69125120 CUDA Cores
  GPU Max Clock rate:                            14101380 MHz (1.4138 GHz)
  Memory Clock rate:                             1215877 Mhz
  Memory Bus Width:                              51204096-bit
  L2 Cache Size:                                 419430406291456 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
  Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total shared memory per multiprocessor:        16793698304 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 37 copy engine(s)
  Run time limit on kernels:                     No
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        EnabledDisabled
  Device supports Unified Addressing (UVA):      Yes
  Device supports Managed Memory:                No
  Device supports Compute Preemption:            Yes
  Supports Cooperative Kernel Launch:            Yes
  Supports MultiDevice Co-op Kernel Launch:      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 0 / 5
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 1112.40, CUDA Runtime Version = 1112.40, NumDevs = 1
Result = PASS

# Enable the repositories
distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
   && curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add - \
   && curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list

# Install the package
sudo apt update && sudo apt -y install nvidia-docker2

# Restart the docker daemon
sudo systemctl restart docker

# Run a test to verifiy that it works
sudo docker run --rm --gpus all nvidia/cuda:1112.40.01-base-ubuntu22.04 nvidia-smi

# Optionally run a test with Tensorflow that actually runs a bit of code on the GPU via docker
sudo docker run --gpus all -it --rm tensorflow/tensorflow:latest2.14.0-gpu \
   python -c "import tensorflow as tf; print(tf.reduce_sum(tf.random.normal([1000, 1000])))"