Ensure to use correct GPU device in RunSince when it's invoked by new thread

[chilo-ms]

Running cuda kernel on incorrect GPU device will end up getting CUDA error: invalid resource handle.

CUDA EP and TRT EP both have this issue when ExecutionMode::ORT_PARALLEL is enabled.

Repro code:

provider = [
        [
            ('TensorrtExecutionProvider', {
            'device_id': 0,
            }),
        ],
        [
            ('TensorrtExecutionProvider', {
            'device_id': 1,
            }),
        ]
       ]

class ThreadObj():
    def __init__(self, model_path: str, iterations: int, idx: int):
       ...
        sess_opt = ort.SessionOptions()
        sess_opt.execution_mode = ort.ExecutionMode.ORT_PARALLEL
        self.inference_session = ort.InferenceSession(model_path, sess_opt, provider[idx % 2])
     
    def warmup(self):
        self.inference_session.run(None, self.input)

    def run(self, thread_times, threads_complete):
        for iter in range(self.iterations):
            self.inference_session.run(None, self.input)

def thread_target(obj, thread_times, threads_complete):
    obj.run(thread_times, threads_complete)

...

iterations = 500
num_threads = 13
t_obj_list = []
thread_list = []

for tidx in range(num_threads):
    obj = ThreadObj(model_path, iterations, tidx)
    t_obj_list.append(obj)
    obj.warmup()
    
for t_obj in t_obj_list:
    thread = threading.Thread(target=thread_target, daemon=True, args=(t_obj,thread_times,threads_complete,))
    thread.start()
    thread_list.append(thread)

...

The reason is when the inference session is initialized, it can be bound to device > 0, whereas when running the inference, i.e. RunSince can be invoked by a new thread and new threads default to using device 0, then we will hit the error of using the incorrect GPU device.
This PR provides a general fix for both CUDA EP and TRT EP to call cudaSetDeivce in RunSince.

[jywu-msft]

Can a test be added for CUDA EP/TRT EP to stress this? (or existing test enhanced)

[chilo-ms]

Can a test be added for CUDA EP/TRT EP to stress this? (or existing test enhanced)

i thought about adding the test but it needs to have multiple GPUs to test.
Checking whether our CI has multiple GPUs or not.