Deepstream execution fails

Hi guys, I just wanted to take a look at the deepstream SDK, but I’m getting stuck on executing the samples.
First of all here are my System-Informations:

• Hardware Platform (Jetson / GPU) → dGPU (GeForce RTX 3070 Laptop GPU)
• DeepStream Version → 6.1
• JetPack Version (valid for Jetson only) →
• TensorRT Version → 8.4
• NVIDIA GPU Driver Version (valid for GPU only) → 510.47.03
• Issue Type( questions, new requirements, bugs) → questions, requirements
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) →
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description) →

When I try to run the samples, they seem to execute and work (so there is no immediate shutdown i.e.), but after some time they brake up and throw errors.

Output for deepstream-test1 (Cuda ver 11.6 set in Makefile)

../deepstream/sources/apps/sample_apps/deepstream-test1$ ./deepstream-test1-app dstest1_config.yml 
Using file: dstest1_config.yml
WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:1482 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.1/sources/apps/sample_apps/deepstream-test1/../../../../samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine open error
0:00:01.195264802 78089 0x5582a74656c0 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1888> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.1/sources/apps/sample_apps/deepstream-test1/../../../../samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed
0:00:01.266011245 78089 0x5582a74656c0 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1993> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.1/sources/apps/sample_apps/deepstream-test1/../../../../samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed, try rebuild
0:00:01.266032057 78089 0x5582a74656c0 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: TensorRT was linked against cuBLAS/cuBLAS LT 11.8.0 but loaded cuBLAS/cuBLAS LT 110.9.2
WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:1454 Serialize engine failed because of file path: /opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine opened error
0:00:23.213474136 78089 0x5582a74656c0 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1941> [UID = 1]: failed to serialize cude engine to file: /opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1         3x368x640       
1   OUTPUT kFLOAT conv2d_bbox     16x23x40        
2   OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40         

0:00:23.288412926 78089 0x5582a74656c0 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary-nvinference-engine> [UID 1]: Load new model:dstest1_pgie_config.yml sucessfully
Running...
Error String : Feature not supported on this GPUError Code : 801
ERROR from element nvv4l2-decoder: Failed to process frame.
Error details: gstv4l2videodec.c(1747): gst_v4l2_video_dec_handle_frame (): /GstPipeline:dstest1-pipeline/nvv4l2decoder:nvv4l2-decoder:
Maybe be due to not enough memory or failing driver
Returned, stopping playback
Deleting pipeline

Output for gstreamer-pipeline (according to FAQ - How can I construct the DeepStream GStreamer pipeline?)

.../deepstream/samples$ gst-launch-1.0 filesrc location = ./streams/sample_1080p_h264.mp4 ! qtdemux ! h264parse ! nvv4l2decoder \
> ! m.sink_0 nvstreammux name=m width=1280 height=720 batch-size=1  ! nvinfer config-file-path= ./configs/deepstream-app/config_infer_primary.txt \
> ! dsexample full-frame=1 ! nvvideoconvert ! nvdsosd ! nveglglessink sync=0
Setting pipeline to PAUSED ...
WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:1482 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/../../models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine open error
0:00:01.220016547 78919 0x563bd7c83130 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1888> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/../../models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed
0:00:01.291913687 78919 0x563bd7c83130 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1993> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/configs/deepstream-app/../../models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed, try rebuild
0:00:01.291935897 78919 0x563bd7c83130 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: TensorRT was linked against cuBLAS/cuBLAS LT 11.8.0 but loaded cuBLAS/cuBLAS LT 110.9.2
WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:1454 Serialize engine failed because of file path: /opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine opened error
0:00:32.412411849 78919 0x563bd7c83130 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1941> [UID = 1]: failed to serialize cude engine to file: /opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1         3x368x640       
1   OUTPUT kFLOAT conv2d_bbox     16x23x40        
2   OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40         

0:00:32.488292581 78919 0x563bd7c83130 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<nvinfer0> [UID 1]: Load new model:./configs/deepstream-app/config_infer_primary.txt sucessfully
Pipeline is PREROLLING ...
Got context from element 'eglglessink0': gst.egl.EGLDisplay=context, display=(GstEGLDisplay)NULL;
Error String : Feature not supported on this GPUError Code : 801
ERROR: from element /GstPipeline:pipeline0/nvv4l2decoder:nvv4l2decoder0: Failed to process frame.
Additional debug info:
gstv4l2videodec.c(1747): gst_v4l2_video_dec_handle_frame (): /GstPipeline:pipeline0/nvv4l2decoder:nvv4l2decoder0:
Maybe be due to not enough memory or failing driver
ERROR: pipeline doesn't want to preroll.
Setting pipeline to NULL ...
Freeing pipeline ...

It seems like there is a Problem with the nvv4l2-decoder…
but to get the whole picture here are some missing implementation-details accordingly to the Deepstream-SDK:

System: Ubuntu 20.04 (upgraded from 18.04, no fresh install)
CUDA: 11.6.2
Gstreamer: 1.16.2
TensorRT: 8.4.0.6-1+cuda11.6

  • I know I could (and probably should) have to check if the problem dissapears when Ubuntu is freshly installed instead of just upgraded… but since I’ve been busy since last week on this topic I just wanted to ensure that the freshy-step is worthwhile. Besides that here are some principal thoughts/questions:

  • The used GeForce RTX 3070 Laptop GPU, should be capable and valid for Deepstream 6.1. Or might this be the cause of the problem?

  • As you can see, I installed mistakly CUDA 11.6.2 instead of 11.6.1. But I assume that this minor Patch should be backwards-compatibile and no Problem at all or is the Deeptstream-SDK actual that restrictive?

  • Although the TensorRT version differs from the one mentioned in the Deepstream-SDK… Well in my defense: I tried to install TensorRT 8.2.5.1, but it won’t succeed (only till CUDA 11.5) because their is no support from CUDA 11.6. (which actually is needed by deepstream). Maybe someone can tell me how to fulfill the mentioned version-requirements anyways… Or should they be that specific different Versions of Cuda: one for TRT and the other one for DS?

  • As I was searching for similar Problems in this Forum and Google and not found any that comparable entries: Where is my fault? Am I missing some little stupid thing?

Thanks in advance and best regards

Please install TensorRT 8.2.5.1 which needs cuda 11.4 for Deepstream SDK 6.1
and install cuda 11.6.1
follow this to setup the environments,
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html#dgpu-setup-for-ubuntu

So actually… nope, it doesn’t help at all.

The “best” result I’m getting so far is identical behavior as before, but without the cuBlast-Warning:

WARNING: [TRT]: TensorRT was linked against cuBLAS/cuBLAS LT 11.8.0 but loaded cuBLAS/cuBLAS LT 110.9.2

But the other errors still remain.

When I install strictly along the Documentation, I get several Errors while installing cuda-11.6 after the driver.run-file:

sudo apt install -y cuda
Reading package lists... Done
Building dependency tree       
Reading state information... Done
cuda is already the newest version (11.6.1-1).
sh: 0: getcwd() failed: No such file or directory
sh: 0: getcwd() failed: No such file or directory
0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
8 not fully installed or removed.
sh: 0: getcwd() failed: No such file or directory
After this operation, 0 B of additional disk space will be used.
sh: 0: getcwd() failed: No such file or directory
Setting up nvidia-dkms-510 (510.47.03-0ubuntu1) ...
update-initramfs: deferring update (trigger activated)

A modprobe blacklist file has been created at /etc/modprobe.d to prevent Nouveau
from loading. This can be reverted by deleting the following file:
/etc/modprobe.d/nvidia-graphics-drivers.conf

A new initrd image has also been created. To revert, please regenerate your
initrd by running the following command after deleting the modprobe.d file:
`/usr/sbin/initramfs -u`

*****************************************************************************
*** Reboot your computer and verify that the NVIDIA graphics driver can   ***
*** be loaded.                                                            ***
*****************************************************************************

INFO:Enable nvidia
DEBUG:Parsing /usr/share/ubuntu-drivers-common/quirks/put_your_quirks_here
DEBUG:Parsing /usr/share/ubuntu-drivers-common/quirks/lenovo_thinkpad
DEBUG:Parsing /usr/share/ubuntu-drivers-common/quirks/dell_latitude
Removing old nvidia-510.47.03 DKMS files...

------------------------------
Deleting module version: 510.47.03
completely from the DKMS tree.
------------------------------
Done.
Loading new nvidia-510.47.03 DKMS files...
Building for 5.4.0-117-generic
Building for architecture x86_64
Building initial module for 5.4.0-117-generic
Error! Application of patch disable_fstack-clash-protection_fcf-protection.patch failed.
Check /var/lib/dkms/nvidia/510.47.03/build/ for more information.
dpkg: error processing package nvidia-dkms-510 (--configure):
 installed nvidia-dkms-510 package post-installation script subprocess returned error exit status 6
dpkg: dependency problems prevent configuration of cuda-drivers-510:
 cuda-drivers-510 depends on nvidia-dkms-510 (>= 510.47.03); however:
  Package nvidia-dkms-510 is not configured yet.

dpkg: error processing package cuda-drivers-510 (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of cuda-drivers:
 cuda-drivers depends on cuda-drivers-510 (= 510.47.03-1); however:
  Package cuda-drivers-510 is not configured yet.

dpkg: error processing package cuda-drivers (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of nvidia-driver-510:
 nvidia-driver-510 depends on nvidia-dkms-510 (= 510.47.03-0ubuntu1); however:
  Package nvidia-dkms-510 is not configured yet.

dpkg: error processing package nvidia-driver-510 (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of cuda-runtNo apport report written because the error message indicates its a followup 
error from a previous failure.
                              No apport report written because the error message indicates its a followup error from a previous failure.
                                                                                                                                       N
o apport report written because MaxReports is reached already
                                                             No apport report written because MaxReports is reached already
                                                                                                                           No apport rep
ort written because MaxReports is reached already
                                                 No apport report written because MaxReports is reached already
                                                                                                               No apport report written 
because MaxReports is reached already
                                     ime-11-6:
 cuda-runtime-11-6 depends on cuda-drivers (>= 510.47.03); however:
  Package cuda-drivers is not configured yet.

dpkg: error processing package cuda-runtime-11-6 (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of cuda-11-6:
 cuda-11-6 depends on cuda-runtime-11-6 (>= 11.6.1); however:
  Package cuda-runtime-11-6 is not configured yet.

dpkg: error processing package cuda-11-6 (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of cuda-demo-suite-11-6:
 cuda-demo-suite-11-6 depends on cuda-runtime-11-6; however:
  Package cuda-runtime-11-6 is not configured yet.

dpkg: error processing package cuda-demo-suite-11-6 (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of cuda:
 cuda depends on cuda-11-6 (>= 11.6.1); however:
  Package cuda-11-6 is not configured yet.

dpkg: error processing package cuda (--configure):
 dependency problems - leaving unconfigured
Processing triggers for initramfs-tools (0.136ubuntu6.7) ...
update-initramfs: Generating /boot/initrd.img-5.4.0-117-generic
Errors were encountered while processing:
 nvidia-dkms-510
 cuda-drivers-510
 cuda-drivers
 nvidia-driver-510
 cuda-runtime-11-6
 cuda-11-6

Seems to me, that the driver.run-installation is conflicting with the cuda-toolkit.
But when I skip this step, the driver will be installed anyways by the cuda-toolkit… and I get the other errors like previously mentioned.

Thanks in advance and best regards

Due to lack of ideas, I went down the fresh-install-road and followed the instructions from: Quickstart Guide — DeepStream 6.1 Release documentation

Install Dependencies

gstreamer, git, etc → success

Install NVIDIA driver 510.47.03

with signed key-pair because of secure-boot → success

Install CUDA Toolkit 11.6.1 (CUDA 11.6 Update 1)

As before boom + driver broken after this:

Reading package lists... Done
Building dependency tree       
Reading state information... Done
cuda-11-6 is already the newest version (11.6.1-1).
The following packages were automatically installed and are no longer required:
  linux-headers-5.13.0-30-generic linux-hwe-5.13-headers-5.13.0-30
  linux-image-5.13.0-30-generic linux-modules-5.13.0-30-generic
  linux-modules-extra-5.13.0-30-generic
  linux-objects-nvidia-470-5.13.0-30-generic
  linux-signatures-nvidia-5.13.0-30-generic
Use 'sudo apt autoremove' to remove them.
0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
7 not fully installed or removed.
After this operation, 0 B of additional disk space will be used.
Setting up nvidia-dkms-510 (510.47.03-0ubuntu1) ...
update-initramfs: deferring update (trigger activated)

A modprobe blacklist file has been created at /etc/modprobe.d to prevent Nouveau
from loading. This can be reverted by deleting the following file:
/etc/modprobe.d/nvidia-graphics-drivers.conf

A new initrd image has also been created. To revert, please regenerate your
initrd by running the following command after deleting the modprobe.d file:
`/usr/sbin/initramfs -u`

*****************************************************************************
*** Reboot your computer and verify that the NVIDIA graphics driver can   ***
*** be loaded.                                                            ***
*****************************************************************************

INFO:Enable nvidia
DEBUG:Parsing /usr/share/ubuntu-drivers-common/quirks/put_your_quirks_here
DEBUG:Parsing /usr/share/ubuntu-drivers-common/quirks/dell_latitude
DEBUG:Parsing /usr/share/ubuntu-drivers-common/quirks/lenovo_thinkpad
Removing old nvidia-510.47.03 DKMS files...

------------------------------
Deleting module version: 510.47.03
completely from the DKMS tree.
------------------------------
Done.
Loading new nvidia-510.47.03 DKMS files...
Building for 5.13.0-51-generic
Building for architecture x86_64
Building initial module for 5.13.0-51-generic
ERROR: Cannot create report: [Errno 17] File exists: '/var/crash/nvidia-dkms-510.0.crash'
Error! Application of patch disable_fstack-clash-protection_fcf-protection.patch failed.
Check /var/lib/dkms/nvidia/510.47.03/build/ for more information.
dpkg: error processing package nvidia-dkms-510 (--configure):
 installed nvidia-dkms-510 package post-installation script subprocess returned error exit status 6
dpkg: dependency problems prevent configuration of cuda-drivers-510:
 cuda-drivers-510 depends on nvidia-dkms-510 (>= 510.47.03); however:
  Package nvidia-dkms-510 is not configured yet.

dpkg: error processing package cuda-drivers-510 (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of cuda-drivers:
 cuda-drivers depends on cuda-drivers-510 (= 510.47.03-1); however:
  Package cuda-drivers-510 is not configured yet.

dpkg: error processing package cuda-drivers (--configure):
 dependency problems - leaving unconfigured
No apport report written because the error message indicates its a followup error from a previous failure.
                          No apport report written because the error message indicates its a followup error from a previous failure.
                                                    No apport report written because MaxReports is reached already
                                  dpkg: dependency problems prevent configuration of nvidia-driver-510:
 nvidia-driver-510 depends on nvidia-dkms-510 (= 510.47.03-0ubuntu1); however:
  Package nvidia-dkms-510 is not configured yet.

dpkg: error processing package nvidia-driver-510 (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of cuda-runtime-11-6:
 cuda-runtime-11-6 depends on cuda-drivers (>= 510.47.03); however:
  Package cuda-drivers is not configured yet.

dpkg: error processing package cuda-runtime-11-6 (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of cuda-11-6:
 cuda-11-6 depends on cuda-runtime-11-6 (>= 11.6.1); however:
  Package cuda-runtime-11-6 is not configured yet.

dpkg: error processing package cuda-11-6 (--configure):
 dependency problems - leaving unconfigured
dpkg: dependency problems prevent configuration of cuda-demo-suite-11-6:
 cuda-demo-suite-11-6 depends on cuda-runtime-11-6; howeNo apport report written because MaxReports is reached already
                                      No apport report written because MaxReports is reached already
                    No apport report written because MaxReports is reached already
  ver:
  Package cuda-runtime-11-6 is not configured yet.

dpkg: error processing package cuda-demo-suite-11-6 (--configure):
 dependency problems - leaving unconfigured
Processing triggers for initramfs-tools (0.136ubuntu6.7) ...
update-initramfs: Generating /boot/initrd.img-5.13.0-51-generic
Errors were encountered while processing:
 nvidia-dkms-510
 cuda-drivers-510
 cuda-drivers
 nvidia-driver-510
 cuda-runtime-11-6
 cuda-11-6
 cuda-demo-suite-11-6
E: Sub-process /usr/bin/dpkg returned an error code (1)

Actually I don’t get it… I mean it is a fresh install and the overall second or third step for the deepstream SDK, so there are not many pitfalls on that way…
If I may allow myself to ask: Are the steps listed in the deepstream SDK tested by nvidia at all?

Sorry for the late.
We tested, and it is working well.
Did this still be an issue?

Yes it is. Actually I am out of ideas and stopped trying/working on the issue.
To summarize it:

  • Install with driver.run before cuda → driver broken + cuda install fails (see above post)
  • no driver.run, inside cuda 11.6 anyways → install cuda + DS-SDK success, but execution fails (see first post)

System setup:
• Hardware Platform (Jetson / GPU) → dGPU (GeForce RTX 3070 Laptop GPU)
• DeepStream Version → 6.1
• Ubuntu Version (fresh install) → 20.04 LTS (with secure-boot)
• TensorRT Version → 8.2.5.1 (cuda 11.4.3)
• NVIDIA GPU Driver Version (valid for GPU only) → 510.47.03

Install setup:

  1. dependencies
  2. (optional) driver
  3. cuda 11.6.1
  4. cudnn 8.4
  5. cuda 11.4.3
  6. tensorrt 8.2.5.1
  7. librdkafka
  8. deepstream 6.1

Thanks so far… in hope for some enlightenment ;)

You can not run deepstream without GPU driver installed. please fix driver issue firstly.

Well I know… as mentioned before:

  • Install with driver.run before cuda → driver broken + cuda install fails (see above post)
  • no driver.run, inside cuda 11.6 anyways → install cuda + DS-SDK success, but execution fails (see first post)

The error you are referencing is far away from trying to run deepstream.
It occurs when I try to install cuda after the driver.run … (as it should be according to SDK-Guide-instructions)
To be more specific:

  1. no driver installed (hint → no external display is active)
  2. download and run the driver.run → succeeds
  3. restart as mentioned in terminal
    (3.) 2nd display is now also active → obviously successful
  4. verify with nvidia-smi → success
  5. trying to install Cuda → driver broken: the error you mentioned

Once again: when I skip the driver.run installation the specified/needed driver 510.47.03 gets installed with Cuda 11.6.1 anyways… So that I can complete the other steps and get deepstream finally installed… but not running.

So there are two issues:

  • Install Error → Install Cuda after the driver.run (see the last 2 codeblocks)
  • Execution Error → (driver.run skipped) deepstream installs but fails on execution (see the first 2 codeblocks)

Remove all the installed driver.
1 install cuda toolkit, do not include cuda drivers.
2 install GPU driver.
3reboot server.

Currently the driver is installed and running successfully:

$ nvidia-smi 
Mon Jun 27 09:52:59 2022       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 510.47.03    Driver Version: 510.47.03    CUDA Version: 11.6     |
|-------------------------------+----------------------+----------------------+

e.g. cuda-samples are running, opencv::cuda module is working

Besides that, I actually don’t know how to exclude the cuda drivers from the toolkit at all.
The command to install the toolkit is: sudo apt install cuda or sudo apt install cuda-11-6
There is no option or interaction to exclude/include specific parts… The process just runs through…
Or what am I missing?

Try sudo apt-get install cuda-toolkit-11-6

Just for info: Currently I’, busy.
I think I will give it try next week or the week after next.

Thanks so far anyways