[BUG] export model report “pthread_setaffinity_np failed for thread”

[enze5088]

Describe the bug
Display during export process

2025-02-20 18:35:48.389281472 [E:onnxruntime:Default, env.cc:234 ThreadMain] pthread_setaffinity_np failed for thread: 113141, index: 3, mask: {14, 46, }, error code: 22 error msg: Invalid argument. Specify the number of threads explicitly so the affinity is not set.
2025-02-20 18:35:48.398061356 [E:onnxruntime:Default, env.cc:234 ThreadMain] pthread_setaffinity_np failed for thread: 113150, index: 12, mask: {26, 58, }, error code: 22 error msg: Invalid argument. Specify the number of threads explicitly so the affinity is not set.
2025-02-20 18:35:48.400097285 [E:onnxruntime:Default, env.cc:234 ThreadMain] pthread_setaffinity_np failed for thread: 113161, index: 23, mask: {17, 49, }, error code: 22 error msg: Invalid argument. Specify the number of threads explicitly so the affinity is not set.
2025-02-20 18:35:48.411123000 [E:onnxruntime:Default, env.cc:234 ThreadMain] pthread_setaffinity_np failed for thread: 113166, index: 28, mask: {27, 59, }, error code: 22 error msg: Invalid argument. Specify the number of threads explicitly so the affinity is not set.
2025-02-20 18:35:48.411130211 [E:onnxruntime:Default, env.cc:234 ThreadMain] pthread_setaffinity_np failed for thread: 113162, index: 24, mask: {21, 53, }, error code: 22 error msg: Invalid argument. Specify the number of threads explicitly so the affinity is not set.

The following information is shown during the reasoning process.

terminate called after throwing an instance of 'onnxruntime::OnnxRuntimeException
what():  /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:123 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, common::Status> = void] /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:116 
std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, common::Status> = void] CUDA failure 700: an illegal memory access was encountered ; GPU=0 ; hostname=tag-second-servcie-datamining-test-776f64b8f5-74lgq ; 
file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_stream_handle.cc ; line=36 ; expr=cudaEventDestroy(event_);

Expected behavior

Images

OS Version:
Ubuntu 20.04

Rembg version:
optimum 1.24.0

Additional context
optimum 1.23.2 can run correctly.