Open
Description
Describe the issue
how does onnxruntime kernel execute,when is to parallelize and when to serialize in device.
I want to know onnx kernel execute seq in onnxruntime,but I do not find the code to control this,is it always serialize?how does it run,please help me with this。
To reproduce
none
Urgency
No response
Platform
Linux
OS Version
18
ONNX Runtime Installation
Built from Source
ONNX Runtime Version or Commit ID
18
ONNX Runtime API
C++
Architecture
X64
Execution Provider
CUDA
Execution Provider Library Version
No response