Not able to download latest CUDA Q version with GPU enabled support

[anastasiapipi]

Required prerequisites

• Consult the security policy. If reporting a security vulnerability, do not report the bug using this form. Use the process described in the policy to report the issue.
• Make sure you've read the documentation. Your issue may be addressed there.
• Search the issue tracker to verify that this hasn't already been reported. +1 or comment there if it has.
• If possible, make a PR with a failing test to give us a starting point to work on!

Describe the bug

I am trying to download the latest CUDA Q version with enabled GPU support using the instructions on the website. I get the following error : nvidia-container-cli: requirement error: unsatisfied condition: cuda>=12.6.

Steps to reproduce the bug

docker run -it --gpus all --name cuda-quantum nvcr.io/nvidia/nightly/cuda-quantum:cu12-latest

output :
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: requirement error: unsatisfied condition: cuda>=12.6, please update your driver to a newer version, or use an earlier cuda container: unknown

Expected behavior

Successful download of CUDA Q with gpu support enabled.

Is this a regression? If it is, put the last known working version (or commit) here.

Not a regression

Environment

• CUDA-Q version: 12.4
• Python version: 3.13.5
• C++ compiler: g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
• • Operating system:
• • NAME="Ubuntu"
    VERSION="20.04.6 LTS (Focal Fossa)"
    ID=ubuntu
    ID_LIKE=debian
    PRETTY_NAME="Ubuntu 20.04.6 LTS"
    VERSION_ID="20.04"
    HOME_URL="https://www.ubuntu.com/"
    SUPPORT_URL="https://help.ubuntu.com/"
    BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/"
    PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy"
    VERSION_CODENAME=focal
    UBUNTU_CODENAME=focal

Suggestions

No response

[khalatepradnya]

@mitchdz - do we support CUDA version 12.4 with the latest changes that have gone in?

[mitchdz]

Thank you Anastasia for making the time to make this bug report.

This behavior is not intended, and you should be able to use this image just fine. We recently updated our build scripts to build an Ubuntu 24.04 image and that now uses CUDA 12.6 to build it. This image should work for any 12.x version, but clearly something went wrong here.

In the meantime, you can try setting NVIDIA_DISABLE_REQUIRE=1 and seeing if that works, but I do foresee the possibility of running into new issues. If you are able to, please try that and let me know if it succeeds/runs into new issues.

There's also the fix of simply updating the driver, but the intent is that you do not have to.

[mitchdz]

@khalatepradnya I haven't had a chance do a full gamut of testing yet, the only one I've done thorough testing is making sure the python wheels can be installed on all CUDA 12.x versions.

[anastasiapipi]

So I used NVIDIA_DISABLE_REQUIRE=1 and it worked, then I exit the terminal and try to rerun the container and I got an error :

docker run -it --gpus all --env NVIDIA_DISABLE_REQUIRE=1 --name cuda-quantum nvcr.io/nvidia/nightly/cuda-quantum:cu12-latest

NVIDIA CUDA-Q

Version: amd64-cu12-latest

Copyright (c) 2025 NVIDIA Corporation & Affiliates
All rights reserved.

To run a command as administrator (user root), use sudo <command>.

cudaq@1cd1210c84f6: exit
logout
(base) anastasiapipi@Lambda: docker run -it --gpus all --env NVIDIA_DISABLE_REQUIRE=1 --name cuda-quantum nvcr.io/nvidia/nightly/cuda-quantum:cu12-latest
Unable to find image 'nvcr.io/nvidia/nightly/cuda-quantum:cu12-latest' locally
cu12-latest: Pulling from nvidia/nightly/cuda-quantum
67b3546b211d: Pull complete
472d23e249b7: Download complete
9c704ecd0c69: Pull complete
.........
75f6e1166953: Pull complete

Digest: sha256:5ce91a484f7b956c5184d63fd1d9034ff989dae8eebf8caba6d629eaaad551cc
Status: Downloaded newer image for nvcr.io/nvidia/nightly/cuda-quantum:cu12-latest
docker: Error response from daemon: could not select device driver "" with capabilities: [[gpu]]

Run 'docker run --help' for more information

[mitchdz]

Anastasia,

That docker error usually goes away after I restart docker

sudo systemctl restart docker

Could you please share which CUDA driver version you have on your system?

[anastasiapipi]

I have tried restarting docker but it still gives me the same error. My driver version is 550.54.15

[mitchdz]

That's interesting. I know I've had that error when I didn't have the container toolkit installed, but it sounds like you do if it worked the first time.

sudo apt install -y nvidia-container-toolkit
sudo systemctl restart docker

Let me see if I can setup a system to match yours and reproduce the original error.

[anastasiapipi]

So I believe I figured it out. After exiting the container, docker context switched to desktop-linux, but after running docker context use default , i can run the --gpus all just fine

[mitchdz]

That's interesting, glad you found a solution to this issue. Are you able to access the container and run anything with cudaq? I'm still setting up my environment.

I'd be really curious if you can run this:

jupyter nbconvert --to notebook --execute ./examples/python/dynamics/dynamics_intro_2.ipynb

[anastasiapipi]

After running the above line in the terminal I get the following error :
ImportError: [CusvsimCircuitSimulator] %forward compatibility was attempted on non supported HW in get_gpu_compatibility (line 38)

[mitchdz]

Thanks for the reply. That's definitely not intended. While you have the system, would you mind giving the output of nvidia-smi?

[mitchdz]

Okay, I set up an Ubuntu 22.04 system with CUDA 12.4 and was able to run the container -

mdzurick@ipp1-0538:~$ nvidia-smi
Fri Oct 17 18:31:16 2025       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.163.01             Driver Version: 550.163.01     CUDA Version: 12.4     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  Tesla V100-PCIE-32GB           Off |   00000000:65:00.0 Off |                    0 |
| N/A   29C    P0             24W /  250W |       5MiB /  32768MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+
mdzurick@ipp1-0538:~$ sudo docker run --rm --gpus all --network host -it nvcr.io/nvidia/nightly/cuda-quantum:cu12-latest
=========================
      NVIDIA CUDA-Q      
=========================

Version: amd64-cu12-latest

Copyright (c) 2025 NVIDIA Corporation & Affiliates 
All rights reserved.

To run a command as administrator (user `root`), use `sudo <command>`.

I know you said you are running Ubuntu 20.04, I wonder if your nvidia-container-toolkit is too old. I have the following installed:

$ apt show nvidia-container-toolkit | grep Version:
Version: 1.17.8-1

[anastasiapipi]

-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.54.15 Driver Version: 550.54.15 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4090 On | 00000000:41:00.0 On | Off |
| 0% 35C P8 33W / 480W | 474MiB / 24564MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 3394 G /usr/lib/xorg/Xorg 35MiB |
| 0 N/A N/A 3777 G /usr/lib/xorg/Xorg 205MiB |
| 0 N/A N/A 3905 G /usr/bin/gnome-shell 44MiB |
| 0 N/A N/A 132767 G /proc/self/exe 89MiB |
| 0 N/A N/A 1915625 G /opt/docker-desktop/Docker Desktop 16MiB |
| 0 N/A N/A 1938430 G /usr/lib/firefox/firefox 0MiB |
+-----------------------------------------------------------------------------------------+

The toolkit version is:
Version: 1.17.8-0lambda0.20.04.1

Also if this might be helpful :
apt-cache policy nvidia-container-toolkit
nvidia-container-toolkit:
Installed: 1.17.8-1
Candidate: 1.17.8-0lambda0.20.04.1

[mitchdz]

Just adding a comment that I am still looking into this.

[mitchdz]

As a quick update, I re-provisioned my system this morning to use Ubuntu 20.04. I was able to start the container. This is how I set up the system, perhaps you can compare to see if there was something different here.

1. Install CUDA via official instructions

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/12.4.0/local_installers/cuda-repo-ubuntu2004-12-4-local_12.4.0-550.54.14-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu2004-12-4-local_12.4.0-550.54.14-1_amd64.deb
sudo cp /var/cuda-repo-ubuntu2004-12-4-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda-toolkit-12-4

2. install and load the driver

sudo apt-get install -y nvidia-driver-550
sudo modprobe nvidia

3. Install nvidia-container-toolkit (adapted from official instructions)

curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
  && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
    sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
    sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update
sudo apt-get install -y nvidia-container-toolkit

4. Install docker

sudo apt-get install -y docker docker.io

5. Pull the docker container

mdzurick@ipp1-0538: ~ 
$ cat /etc/os-release | grep PRETTY
PRETTY_NAME="Ubuntu 20.04.6 LTS"
mdzurick@ipp1-0538: ~ 
$ sudo docker run --rm --gpus all --network host -it nvcr.io/nvidia/nightly/cuda-quantum:cu12-latest
=========================
      NVIDIA CUDA-Q      
=========================

Version: amd64-cu12-latest

Copyright (c) 2025 NVIDIA Corporation & Affiliates 
All rights reserved.

To run a command as administrator (user `root`), use `sudo <command>`.


cudaq@ipp1-0538:~$ nvidia-smi | grep Version
| NVIDIA-SMI 550.54.14              Driver Version: 550.54.14      CUDA Version: 12.6     |
cudaq@ipp1-0538:~$ exit
logout
mdzurick@ipp1-0538: ~ 
$ nvidia-smi | grep Version
| NVIDIA-SMI 550.54.14              Driver Version: 550.54.14      CUDA Version: 12.4     |