You are running using the stub version of nvrtc

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) - T4
• DeepStream Version - 6.0-devel docker
• TensorRT Version - 6.0-devel docker
• NVIDIA GPU Driver Version - 440.33.01
• Issue Type - Question - Warning Logs

I’m gettig these Error and Warnings messages when running a merged modified verion of deepstream test app 4 and deepstream reference app with dynamic source add delete. Will these warnings cause production level issues or performance bottlenecks?

ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:1484 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine open error
0:00:01.108794113     7 0x7f7b7caf8690 WARN                 nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1889> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed
0:00:01.108849489     7 0x7f7b7caf8690 WARN                 nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1996> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed, try rebuild
0:00:01.108861927     7 0x7f7b7caf8690 INFO                 nvinfer gstnvinfer.cpp:638: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

You are running using the stub version of nvrtc
.
You are running using the stub version of nvrtc
.
You are running using the stub version of nvrtc
.WARNING: [TRT]: Convolution + generic activation fusion is disable due to incompatible driver or nvrtc
WARNING: [TRT]: Detected invalid timing cache, setup a local cache instead

I understand that the engine files do not exist the first time I run the application. I’m worried about the other messages - “You are running using the stub version of nvrtc” and “Convolution + generic activation fusion is disable”

Is there any issue except the log?

I didn’t notice any issues yet, but I’m concerned about the quality of the TRT engine file generated, and about the FPS of the application because the log says I’m using the stub version of nvrtc.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.