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

The below link might be useful for you
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.