ERROR: engine.cpp (370) - Cuda Error in ~ExecutionContext: 77

I do Int8 calibration using TensorRT.

Once calibration is completed and test the inference. I have error at


in the following function.

No issue running on FP32 and FP16 engines. Only have error running at Int8 engine. What could be wrong?

def infer(engine, x, batch_size, context):
  inputs = []
  outputs = []
  bindings = []
  stream = cuda.Stream()
  for binding in engine:
    size = trt.volume(engine.get_binding_shape(binding)) * batch_size
    dtype = trt.nptype(engine.get_binding_dtype(binding))
    # Allocate host and device buffers
    host_mem = cuda.pagelocked_empty(size, dtype)
    device_mem = cuda.mem_alloc(host_mem.nbytes)
    # Append the device buffer to device bindings.
    # Append to the appropriate list.
    if engine.binding_is_input(binding):
      inputs.append(HostDeviceMem(host_mem, device_mem))
      outputs.append(HostDeviceMem(host_mem, device_mem))
    #img = np.array(x).ravel()
    im = np.array(x, dtype=np.float32, order='C')
    im = im[:,:,::-1]
    #im = im.transpose((2,0,1))
    #np.copyto(inputs[0].host, x.flatten())  #1.0 - img / 255.0
    np.copyto(inputs[0].host, im.flatten())
    [cuda.memcpy_htod_async(inp.device,, stream) for inp in inputs]
    context.execute_async(batch_size=batch_size, bindings=bindings, stream_handle=stream.handle)
    # Transfer predictions back from the GPU.
    [cuda.memcpy_dtoh_async(, out.device, stream) for out in outputs]
    # Synchronize the stream
    # Return only the host outputs.