Segmentation fault with multithreaded engine build

Update update? @ NVES_R

We met this same issue too on Windows 10 + trt7.2.2.3 + cuda 11.1 on RTX3090.
Refer to here: Crash in TensorRT during converting the ONNX model to PLAN in parallel · Issue #1594 · NVIDIA/TensorRT · GitHub

Hi,
The below link might be useful for you
https://docs.nvidia.com/deeplearning/tensorrt/best-practices/index.html#thread-safety
https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#stream-priorities
https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__STREAM.html
For multi threading/streaming, will suggest you to use Deepstream or TRITON
For more details, we recommend you to raise the query to the Deepstream or TRITON forum.

Thanks!