Update export_vision.py

[keeper-jie]

fix do not generate rotary_pos_emb and cu_seqlens npy file error

bug discription:

When I try to follow the readme file generate  rotary_pos_emb and cu_seqlens npy file, there is no file generate. So I fix it and it work as expected.

before

Traceback (most recent call last):
  File "/dataset/rknn-llm/examples/Qwen2-VL_Demo/export/export_vision.py", line 89, in <module>
    torch.onnx.export(model, pixel_values, args.savepath, opset_version=18)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/onnx/utils.py", line 516, in export
    _export(
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/onnx/utils.py", line 1612, in _export
    graph, params_dict, torch_out = _model_to_graph(
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/onnx/utils.py", line 1134, in _model_to_graph
    graph, params, torch_out, module = _create_jit_graph(model, args)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/onnx/utils.py", line 1010, in _create_jit_graph
    graph, torch_out = _trace_and_get_graph_from_model(model, args)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/onnx/utils.py", line 914, in _trace_and_get_graph_from_model
    trace_graph, torch_out, inputs_states = torch.jit._get_trace_graph(
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/jit/_trace.py", line 1310, in _get_trace_graph
    outs = ONNXTracedModule(
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/jit/_trace.py", line 138, in forward
    graph, out = torch._C._create_graph_by_tracing(
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/jit/_trace.py", line 129, in wrapper
    outs.append(self.inner(*trace_inputs))
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1522, in _slow_forward
    result = self.forward(*input, **kwargs)
  File "/dataset/rknn-llm/examples/Qwen2-VL_Demo/export/export_vision.py", line 52, in export_onnx
    feature = model.visual(flatten_patches)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
    return forward_call(*args, **kwargs)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1522, in _slow_forward
    result = self.forward(*input, **kwargs)
  File "/dataset/rknn-llm/examples/Qwen2-VL_Demo/export/export_vision.py", line 68, in tmp
    rotary_pos_emb = torch.from_numpy(np.load("./rotary_pos_emb.npy")).to(dtype=hidden_states.dtype, device=hidden_states.device)
  File "/root/miniconda3/envs/llm_310/lib/python3.10/site-packages/numpy/lib/npyio.py", line 427, in load
    fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: './rotary_pos_emb.npy'

after

==========================================================
Generating the rotary_pos_emb and cu_seqlens done.
grid_thw tensor([[ 1, 28, 28]])
The attention layers in this model are transitioning from computing the RoPE embeddings internally through `rotary_pos_emb` (2D tensor of RoPE theta values), to using externally computed `position_embeddings` (Tuple of tensors, containing cos and sin). In v4.54 `rotary_pos_emb` will be removed and `position_embeddings` will be mandatory.