Unable to run Audio2Face in AWS using Tesla T4 & A10G Gpus

kit_20220411_123718.log (287.7 KB)

I’ve been trying to make Audio2Face work in AWS on multiple configurations. I’ve tried Windows Server 2019, 2022, with either Tesla T4 & A10G GPUs with appropriate Nvidia drivers for each.

While on Windows server 2019 I wasn’t able to launch Audio2Face at all since it kept requiring to update to a newer Windows build even though I was on the latest build for Windows server 2019, I did manage to launch it on Windows Server 2022.

The first error that pops up is:

2022-04-11 12:37:24 [Error] [gpu.foundation.plugin] No device could be created. Some known system issues:

  • The driver is not installed properly and requires a clean re-install.
  • Your GPUs do not support RayTracing: DXR or Vulkan ray_tracing, or hardware is excluded due to performance.
  • The driver cannot enumerate any GPU: driver, display or a docker issue. For Vulkan, test it with Vulkaninfo tool from Vulkan SDK, instead of nvidia-smi.

I got a bunch of other errors following this on. You can check them out in the attached log file.
Can anyone confirm that Tesla T4 & A10G GPUs are supported? According to what I’ve read online, both of them should support RTX.

Please let me know if I’m missing something.

nvidia-smi output:
| NVIDIA-SMI 511.65 Driver Version: 511.65 CUDA Version: 11.6 |
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
| 0 NVIDIA A10G TCC | 00000000:00:1E.0 Off | 0 |
| 0% 32C P0 59W / 300W | 246MiB / 23028MiB | 0% Default |
| | | N/A |

| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
| 0 N/A N/A 9028 C …face-2021.3.3\kit\kit.exe 245MiB |

Appreciate the help,

Hi @romanm Sorry for the issues you encounter.
This sounds like the kit sdk and os compatibility issue, or have you managed to run other app on the same os and hardware configuration?
I’ll ping and get our kit team to confirm this.