# Running depth\_anything\_v2 from holohub on DGX Spark **URL:** \ **Category:** General\ **Created:** [December 11, 2025, 8:02am UTC](https://forums.developer.nvidia.com/t/running-depth-anything-v2-from-holohub-on-dgx-spark/354282 "2025-12-11T08:02:32Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![ralph.harti](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@ralph.harti](https://forums.developer.nvidia.com/u/ralph.harti)\ **Post date:** [December 11, 2025, 8:02am UTC](https://forums.developer.nvidia.com/t/running-depth-anything-v2-from-holohub-on-dgx-spark/354282/1 "2025-12-11T08:02:32Z")
Hi, I am trying to run the depth\_anything\_v2 application from holoscan on the DGX Spark, but I seem to run into issues with holoviz. Any ideas what I could do? Thanks a lot [info] [context.cpp:54] \_\_\_\_\_\_\_\_\_\_\_\_\_\_\_ [info] [context.cpp:54] Vulkan Version: [info] [context.cpp:54] - available: 1.3.275 [info] [context.cpp:54] - requesting: 1.2.0 [warning] [context.cpp:57] VK\_ERROR\_EXTENSION\_NOT\_PRESENT: VK\_KHR\_display - 0 [error] [gxf\_wrapper.cpp:69] Exception occurred when starting operator: ‘holoviz’ - Failed to create the Vulkan instance. [warning] [entity\_executor.cpp:674] Failed to start entity [holoviz] [warning] [greedy\_scheduler.cpp:243] Error while executing entity 47 named ‘holoviz’: GXF\_FAILURE [error] [entity\_executor.cpp:789] Entity [holoviz] must be in Started, Tick Pending, Ticking or Idle stage before stopping. Current state is StartPending [info] [greedy\_scheduler.cpp:401] Scheduler finished. [error] [program.cpp:580] wait failed. Deactivating… [error] [runtime.cpp:1655] Graph wait failed with error: GXF\_FAILURE [warning] [gxf\_executor.cpp:2548] GXF call GxfGraphWait(context) in line 2548 of file /workspace/holoscan-sdk/src/core/executors/gxf/gxf\_executor.cpp failed with ‘GXF\_FAILURE’ (1) [info] [gxf\_executor.cpp:2563] [Depth Anything V2 App] Graph execution finished. [error] [gxf\_executor.cpp:2571] [Depth Anything V2 App] Graph execution error: GXF\_FAILURE Traceback (most recent call last): File “/workspace/holohub/applications/depth\_anything\_v2/depth\_anything\_v2.py”, line 312, in main() File “/workspace/holohub/applications/depth\_anything\_v2/depth\_anything\_v2.py”, line 308, in main app.run() RuntimeError: Failed to create the Vulkan instance. [info] [gxf\_executor.cpp:432] [Depth Anything V2 App] Destroying context Non-zero exit code running command: python3 /workspace/holohub/applications/depth\_anything\_v2/depth\_anything\_v2.py Exit code: 1 Non-zero exit code running command: docker run --net host --interactive --tty -u 0:0 -v /etc/group:/etc/group:ro -v /etc/passwd:/etc/passwd:ro -v /home/hexagonme/repos/holohub:/workspace/holohub -w /workspace/holohub --gpus all --cap-add CAP\_SYS\_PTRACE --ipc=host -v /dev:/dev --device-cgroup-rule “c 81:\* rmw” --device-cgroup-rule “c 189:\* rmw” -e NVIDIA\_DRIVER\_CAPABILITIES=graphics,video,compute,utility,display -e HOME=/workspace/holohub -e CUPY\_CACHE\_DIR=/workspace/holohub/.cupy/kernel\_cache -e HOLOHUB\_BUILD\_LOCAL=1 --rm --ipc=host --cap-add=CAP\_SYS\_PTRACE --ulimit=memlock=-1 --ulimit=stack=67108864 --device /dev/video1 --device /dev/video0 --device /dev/snd/controlC1 --device /dev/snd/controlC0 --device /dev/snd/pcmC1D0c --device /dev/snd/pcmC0D9p --device /dev/snd/pcmC0D8p --device /dev/snd/pcmC0D7p --device /dev/snd/pcmC0D3p --device /dev/snd/timer --device /dev/snd/seq --device /dev/infiniband/rdma\_cm --device /dev/infiniband/uverbs3 --device /dev/infiniband/uverbs2 --device /dev/infiniband/uverbs1 --device /dev/infiniband/uverbs0 -v /usr/lib/aarch64-linux-gnu/nvidia:/usr/lib/aarch64-linux-gnu/nvidia --device /dev/nvidia0 --device /dev/nvidia-modeset -v /usr/share/nvidia/nvoptix.bin:/usr/share/nvidia/nvoptix.bin:ro --group-add 44 --group-add 993 --group-add 988 --group-add 29 -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY -e PYTHONPATH=/opt/nvidia/holoscan/python/lib:/workspace/holohub/benchmarks/holoscan\_flow\_benchmarking --entrypoint=/bin/ ---
**Author:** ![aheumann](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aheumann/32/382649_2.png) [@aheumann](https://forums.developer.nvidia.com/u/aheumann)\ **Post date:** [December 11, 2025, 9:17am UTC](https://forums.developer.nvidia.com/t/running-depth-anything-v2-from-holohub-on-dgx-spark/354282/2 "2025-12-11T09:17:42Z")
Hi, It seems the `VK_KHR_display` extension is not found. Maybe there is some problem with the NVIDIA driver installation. Is any Holohub application using Holoviz working? Could you post the output of `nvidia-smi` and `vulkaninfo`? Andreas ---
**Author:** ![ralph.harti](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@ralph.harti](https://forums.developer.nvidia.com/u/ralph.harti)\ **Post date:** [December 11, 2025, 12:54pm UTC](https://forums.developer.nvidia.com/t/running-depth-anything-v2-from-holohub-on-dgx-spark/354282/3 "2025-12-11T12:54:47Z")
Hi, Thanks a lot for the quick reply. **Here is the output of nvidia-smi:** Thu Dec 11 13:43:12 2025 ±----------------------------------------------------------------------------------------+ | NVIDIA-SMI 580.95.05 Driver Version: 580.95.05 CUDA Version: 13.0 | ±----------------------------------------±-----------------------±---------------------+ | 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 GB10 On | 0000000F:01:00.0 Off | N/A | | N/A 38C P8 3W / N/A | Not Supported | 0% Default | | | | N/A | ±----------------------------------------±-----------------------±---------------------+ ±----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 2385 G /usr/lib/xorg/Xorg 18MiB | | 0 N/A N/A 2680 G /usr/bin/gnome-shell 6MiB | **And this is the top of vulkaninfo:** ‘DISPLAY’ environment variable not set… skipping surface info TU: error: ../src/freedreno/vulkan/tu\_knl.cc:385: failed to open device /dev/dri/renderD128 (VK\_ERROR\_INCOMPATIBLE\_DRIVER) # VULKANINFO Vulkan Instance Version: 1.4.328 Could that be the issue? I get the exact same **holoviz error** , as reported above, when running the endoscopy\_depth\_estimation application in holohub. Thanks ---
**Author:** ![aheumann](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aheumann/32/382649_2.png) [@aheumann](https://forums.developer.nvidia.com/u/aheumann)\ **Post date:** [December 11, 2025, 1:47pm UTC](https://forums.developer.nvidia.com/t/running-depth-anything-v2-from-holohub-on-dgx-spark/354282/4 "2025-12-11T13:47:57Z")
It seems when you ran the `vulkaninfo` command the X11 `DISPLAY` env variable was not set, therefore that error. Could you set the `DISPLAY` env variable or and run `vulkaninfo –summary`? This should give you something like that (this one is from a different machine with a different driver, not a DGX Spark). This should list the `VK_KHR_display` extension. # VULKANINFO Vulkan Instance Version: 1.3.204 ## Instance Extensions: count = 19 VK\_EXT\_acquire\_drm\_display : extension revision 1 VK\_EXT\_acquire\_xlib\_display : extension revision 1 VK\_EXT\_debug\_report : extension revision 10 VK\_EXT\_debug\_utils : extension revision 2 VK\_EXT\_direct\_mode\_display : extension revision 1 VK\_EXT\_display\_surface\_counter : extension revision 1 VK\_KHR\_device\_group\_creation : extension revision 1 VK\_KHR\_display : extension revision 23 VK\_KHR\_external\_fence\_capabilities : extension revision 1 VK\_KHR\_external\_memory\_capabilities : extension revision 1 VK\_KHR\_external\_semaphore\_capabilities : extension revision 1 VK\_KHR\_get\_display\_properties2 : extension revision 1 VK\_KHR\_get\_physical\_device\_properties2 : extension revision 2 VK\_KHR\_get\_surface\_capabilities2 : extension revision 1 VK\_KHR\_surface : extension revision 25 VK\_KHR\_surface\_protected\_capabilities : extension revision 1 VK\_KHR\_wayland\_surface : extension revision 6 VK\_KHR\_xcb\_surface : extension revision 6 VK\_KHR\_xlib\_surface : extension revision 6 ## Instance Layers: count = 1 VK\_LAYER\_NV\_optimus NVIDIA Optimus layer 1.3.242 version 1 # Devices: GPU0: apiVersion = 4206834 (1.3.242) driverVersion = 2244247680 (0x85c48080) vendorID = 0x10de deviceID = 0x2231 deviceType = PHYSICAL\_DEVICE\_TYPE\_DISCRETE\_GPU deviceName = NVIDIA RTX A5000 driverID = DRIVER\_ID\_NVIDIA\_PROPRIETARY driverName = NVIDIA driverInfo = 535.274.02 conformanceVersion = 1.3.5.0 deviceUUID = b92362b2-d370-b8c4-1906-9cd06ed5e776 driverUUID = c7a06fe8-360b-526e-80cc-067a2a45ae5f Could you also try to run `vkcube` and see if that simple Vulkan application is running correctly? There might be several reasons that `depth_anything_2` did not run. One is that the display driver is now working correctly for whatever reason. Another one might be docker setup since `depth_anything_2` is running inside a docker container. It would be good to know if `vkcube`and `vulkaninfo` work both bare metal and inside a docker container to isolate the root cause. Andreas ---
**Author:** ![ralph.harti](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@ralph.harti](https://forums.developer.nvidia.com/u/ralph.harti)\ **Post date:** [December 15, 2025, 8:33am UTC](https://forums.developer.nvidia.com/t/running-depth-anything-v2-from-holohub-on-dgx-spark/354282/5 "2025-12-15T08:33:58Z")
Setting the display variable gives me the following vulkaninfo –summary output: ========== VULKANINFO Vulkan Instance Version: 1.4.328 ## Instance Extensions: count = 25 VK\_EXT\_acquire\_drm\_display : extension revision 1 VK\_EXT\_acquire\_xlib\_display : extension revision 1 VK\_EXT\_debug\_report : extension revision 10 VK\_EXT\_debug\_utils : extension revision 2 VK\_EXT\_direct\_mode\_display : extension revision 1 VK\_EXT\_display\_surface\_counter : extension revision 1 VK\_EXT\_headless\_surface : extension revision 1 VK\_EXT\_surface\_maintenance1 : extension revision 1 VK\_EXT\_swapchain\_colorspace : extension revision 5 VK\_KHR\_device\_group\_creation : extension revision 1 VK\_KHR\_display : extension revision 23 VK\_KHR\_external\_fence\_capabilities : extension revision 1 VK\_KHR\_external\_memory\_capabilities : extension revision 1 VK\_KHR\_external\_semaphore\_capabilities : extension revision 1 VK\_KHR\_get\_display\_properties2 : extension revision 1 VK\_KHR\_get\_physical\_device\_properties2 : extension revision 2 VK\_KHR\_get\_surface\_capabilities2 : extension revision 1 VK\_KHR\_portability\_enumeration : extension revision 1 VK\_KHR\_surface : extension revision 25 VK\_KHR\_surface\_protected\_capabilities : extension revision 1 VK\_KHR\_wayland\_surface : extension revision 6 VK\_KHR\_xcb\_surface : extension revision 6 VK\_KHR\_xlib\_surface : extension revision 6 VK\_LUNARG\_direct\_driver\_loading : extension revision 1 VK\_NV\_display\_stereo : extension revision 1 ## Instance Layers: count = 4 VK\_LAYER\_MESA\_device\_select Linux device selection layer 1.4.303 version 1 VK\_LAYER\_MESA\_overlay Mesa Overlay layer 1.4.303 version 1 VK\_LAYER\_NV\_optimus NVIDIA Optimus layer 1.4.312 version 1 VK\_LAYER\_NV\_present NVIDIA GR2608 layer 1.4.312 version 1 # Devices: GPU0: apiVersion = 1.4.312 driverVersion = 580.95.5.0 vendorID = 0x10de deviceID = 0x2e12 deviceType = PHYSICAL\_DEVICE\_TYPE\_INTEGRATED\_GPU deviceName = NVIDIA Tegra NVIDIA GB10 driverID = DRIVER\_ID\_NVIDIA\_PROPRIETARY driverName = NVIDIA driverInfo = 580.95.05 conformanceVersion = 1.4.1.3 deviceUUID = 7e67e374-fd89-8bf9-9d17-30a454984aa7 driverUUID = b92269a1-b525-5615-ab8a-e2095ee37192 GPU1: apiVersion = 1.4.305 driverVersion = 0.0.1 vendorID = 0x10005 deviceID = 0x0000 deviceType = PHYSICAL\_DEVICE\_TYPE\_CPU deviceName = llvmpipe (LLVM 20.1.2, 128 bits) driverID = DRIVER\_ID\_MESA\_LLVMPIPE driverName = llvmpipe driverInfo = Mesa 25.0.7-0ubuntu0.24.04.2 (LLVM 20.1.2) conformanceVersion = 1.3.1.1 deviceUUID = 6d657361-3235-2e30-2e37-2d3075627500 driverUUID = 6c6c766d-7069-7065-5555-494400000000 Looks good from what I can tell in regards to the VK\_KHR\_display extension. vkcube is also successful and a cube is rendered. When I enter the docker container with docker run --rm -it --entrypoint bash holohub:depth\_anything\_v2 Neither vulkaninfo nor vkcube are found. Thanks, Ralph ---
**Author:** ![aheumann](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aheumann/32/382649_2.png) [@aheumann](https://forums.developer.nvidia.com/u/aheumann)\ **Post date:** [December 15, 2025, 9:54am UTC](https://forums.developer.nvidia.com/t/running-depth-anything-v2-from-holohub-on-dgx-spark/354282/6 "2025-12-15T09:54:34Z")
Indeed, it looks good outside of the docker container. `vulkaninfo` and `vkcube` are part of the `vulkan-tools` package. You have to install it in the container using `apt update && apt install vulkan-tools`. Also make sure to run the container with `--runtime nvidia` and run `nvidia-smi` to see if the GPU is available. ---
**Author:** ![ralph.harti](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@ralph.harti](https://forums.developer.nvidia.com/u/ralph.harti)\ **Post date:** [December 15, 2025, 1:02pm UTC](https://forums.developer.nvidia.com/t/running-depth-anything-v2-from-holohub-on-dgx-spark/354282/7 "2025-12-15T13:02:39Z")
I ended up getting it to work by starting the docker container not via dockerhub, but using the docker run command seperately. It worked fine if I executed this: docker run --net host --interactive --tty -u 1000:1000 -v /etc/group:/etc/group:ro -v /etc/passwd:/etc/passwd:ro -v /home/hexagonme/repos/holohub:/workspace/holohub -w /workspace/holohub --gpus all --cap-add CAP\_SYS\_PTRACE --ipc=host -v /dev:/dev --device-cgroup-rule “c 81:\* rmw” --device-cgroup-rule “c 189:\* rmw” -e NVIDIA\_DRIVER\_CAPABILITIES=graphics,video,compute,utility,display -e HOME=/workspace/holohub -e CUPY\_CACHE\_DIR=/workspace/holohub/.cupy/kernel\_cache -e HOLOHUB\_BUILD\_LOCAL=1 --rm --ipc=host --cap-add=CAP\_SYS\_PTRACE --ulimit=memlock=-1 --ulimit=stack=67108864 --device /dev/video1 --device /dev/video0 --device /dev/snd/controlC1 --device /dev/snd/controlC0 --device /dev/snd/pcmC1D0c --device /dev/snd/pcmC0D9p --device /dev/snd/pcmC0D8p --device /dev/snd/pcmC0D7p --device /dev/snd/pcmC0D3p --device /dev/snd/timer --device /dev/snd/seq --device /dev/infiniband/rdma\_cm --device /dev/infiniband/uverbs3 --device /dev/infiniband/uverbs2 --device /dev/infiniband/uverbs1 --device /dev/infiniband/uverbs0 -v /usr/lib/aarch64-linux-gnu/nvidia:/usr/lib/aarch64-linux-gnu/nvidia --device /dev/nvidia0 --device /dev/nvidia-modeset -v /usr/share/nvidia/nvoptix.bin:/usr/share/nvidia/nvoptix.bin:ro --group-add 44 --group-add 993 --group-add 988 --group-add 29 -e XDG\_SESSION\_TYPE -e XDG\_RUNTIME\_DIR -v /run/user/1000:/run/user/1000 -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY -e PYTHONPATH=/opt/nvidia/holoscan/python/lib:/workspace/holohub/benchmarks/holoscan\_flow\_benchmarking -e DISPLAY=:1 --runtime=nvidia --entrypoint=/bin/bash holohub-depth\_anything\_v2:8cba8281cf92 -c “./holohub run depth\_anything\_v2 --language python --local” No sure why it gets hung up with holohub…. Thanks a lot for you help Andreas. ---
**Author:** ![aheumann](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aheumann/32/382649_2.png) [@aheumann](https://forums.developer.nvidia.com/u/aheumann)\ **Post date:** [December 16, 2025, 6:59am UTC](https://forums.developer.nvidia.com/t/running-depth-anything-v2-from-holohub-on-dgx-spark/354282/8 "2025-12-16T06:59:31Z")
Great, glad that I could help.