NVIDIA Parabricks v4.3.1-1 cant detect the GPU

Dear,
I tried to test the Parabricks pipeline. I installed the Parabricks v4.3.1 docker container. When I tried to run the command I got the following error:

[Parabricks Options Mesg]: Note: fq2bam will become an alias fq2bamfast in the next major release
[PB Info 2024-Jun-07 07:54:40] ------------------------------------------------------------------------------
[PB Info 2024-Jun-07 07:54:40] || Parabricks accelerated Genomics Pipeline ||
[PB Info 2024-Jun-07 07:54:40] || Version 4.3.1-1 ||
[PB Info 2024-Jun-07 07:54:40] || GPU-BWA mem, Sorting Phase-I ||
[PB Info 2024-Jun-07 07:54:40] ------------------------------------------------------------------------------
[M::bwa_idx_load_from_disk] read 0 ALT contigs
[PB Error 2024-Jun-07 07:54:45][ParaBricks/src/pbOpts.cu:107] Bad argument value: Number of GPUs requested (1) is more than number of GPUs (0in the system., exiting.
For technical support visit NVIDIA Clara - NVIDIA Docs
Exiting…

=====================
While the Parabricks v4.2.1-1 is working perfectly fine and can detect the GPU device we have:

and as you can see its running fine:

Fri Jun 7 07:55:47 2024
±--------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.171.04 Driver Version: 535.171.04 CUDA Version: 12.2 |
|-----------------------------------------±---------------------±---------------------+
| 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 3090 Off | 00000000:20:00.0 Off | N/A |
| 35% 53C P8 22W / 350W | 260MiB / 24576MiB | 0% Default |
| | | N/A |
±----------------------------------------±---------------------±---------------------+

±--------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| 0 N/A N/A 5992 C …al/parabricks/binaries/bin/postsort 254MiB |
±--------------------------------------------------------------------------------------+

Any suggestion?

Kind regards

could you share the whole command line you used for the pipeline invocation?

You may need to update your driver to 12.3+. Forward compatibility is generally only for data center GPUs.

https://docs.nvidia.com/deploy/cuda-compatibility/#forward-compatibility