Multiple Cuda Context and multi threading about insightface-rest HOT 4 CLOSED

PyCUDA ERROR: The context stack was not empty upon module cleanup.
-------------------------------------------------------------------
A context was still active when the context stack was being
cleaned up. At this point in our execution, CUDA may already
have been deinitialized, so there is no way we can finish
cleanly. The program will be aborted now.
Use Context.pop() to avoid this problem.

class TrtModel(object):
    def __init__(self, model):
        self.cfx = None
        self.engine_file = model
        self.engine = None
        self.inputs = None
        self.outputs = None
        self.bindings = None
        self.stream = None
        self.context = None
        self.input_shapes = None
        self.out_shapes = None
        self.max_batch_size = 1

    def build(self):
        self.cfx = cuda.Device(0).make_context()
        with open(self.engine_file, 'rb') as f, trt.Runtime(TRT_LOGGER) as runtime:
            self.engine = runtime.deserialize_cuda_engine(f.read())
        self.inputs, self.outputs, self.bindings, self.stream, self.input_shapes, self.out_shapes, self.out_names, self.max_batch_size = allocate_buffers(
            self.engine)

        self.context = self.engine.create_execution_context()
        self.context.active_optimization_profile = 0

    def run(self, input, deflatten: bool = True, as_dict=False):
        threading.Thread.__init__(self)
        self.cfx.push()
        # lazy load implementation
        engine = self.engine
        bindings = self.bindings
        inputs = self.inputs
        outputs = self.outputs
        stream = self.stream
        context = self.context
        out_shapes = self.out_shapes
        out_names = self.out_names
        if engine is None:
            self.build()

        input = np.asarray(input)
        batch_size = input.shape[0]
        allocate_place = np.prod(input.shape)
        inputs[0].host[:allocate_place] = input.flatten(order='C').astype(np.float32)
        context.set_binding_shape(0, input.shape)
        trt_outputs = do_inference(
            context, bindings=bindings,
            inputs=inputs, outputs=outputs, stream=stream)
        #Reshape TRT outputs to original shape instead of flattened array
        if deflatten:
            trt_outputs = [output.reshape(shape) for output, shape in zip(trt_outputs, out_shapes)]
        if as_dict:
            return {name: trt_outputs[i] for i, name in enumerate(self.out_names)}
        # self.cfx.pop()
        return [trt_outputs[0][:batch_size]]

    def destroy(self):
        self.cfx.pop()
        del self.cfx
        del self.engine

det_model = thread_buckets[thread_name]['det_model']
        rec_model = thread_buckets[thread_name]['rec_model']
        processor_thread = thread_buckets[thread_name]['processor_thread']
        processor_thread.kill()
        processor_thread.join()
        det_model.retina.model.rec_model.destroy()
        rec_model.rec_model.destroy()
        del det_model
        del rec_model
        del thread_buckets[thread_name]