Open motidil opened 2 years ago
You don't have gpu support in your container then. Check available documentation on how to enable the nvidia runtime for docker.
I don't think that is the case...I'm able to run other tasks with GPU and cuda.
attach here nvidia-smi
output in the container:
root@550dd14d9c34:/yolov4-triton-tensorrt/build# nvidia-smi
Mon Jul 18 13:36:17 2022
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 515.48.07 Driver Version: 515.48.07 CUDA Version: 11.7 |
|-------------------------------+----------------------+----------------------+
| 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 T4G Off | 00000000:00:1F.0 Off | 0 |
| N/A 53C P0 28W / 70W | 2MiB / 15360MiB | 5% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| No running processes found |
+-----------------------------------------------------------------------------+
I'm trying to run the build stage using
nvcr.io/nvidia/tensorrt:22.05-py3
but stuck on themake
step with the following error:OS ubuntu 20.04 ARCH: ARM64 In container: NVIDIA Release 22.05 (build 37412549) NVIDIA TensorRT Version 8.2.5