Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) GPU RTX 4060
• DeepStream Version 6.2 or 6.4
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.5 or 8.6
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) bugs
• 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)
Reproduce
I am working with deepstream and nvidia-tao.
With RTX 3060, with the code taken from deepstream python app, i created a pgie config file with tao etlt model, then I successfully to convert the .etll model to tensorrt engine.
However, with RTX 4060 I got an error LLVM ERROR: out of memory (DS6.4 and trt 8.6). The log detail is below:
Creating Pipeline
Creating streammux
Creating source_bin 0
Creating uridecodebin for [file:///ws/threat_detection/version_007_14.mp4]
source-bin-00
Creating Pgie
Creating nv optical flow element
Creating tiler
Creating nvvidconv
Creating nvosd
Creating H264 Encoder
Creating H264 rtppay
Adding elements to Pipeline
Linking elements in the Pipeline
LLVM ERROR: out of memory
Aborted (core dumped)
Please help me to check it