Assertion error with app demo

[KW-NJU]

Hi, when I was running:
python -m demo.app --resume_from_checkpoint chenjoya/videollm-online-8b-v1plus --attn_implementation sdpa

I got a strange error. When I tried to ask a question on the web page, Assitant's reply would always get stuck at various places and report errors. The error on the terminal is:

Traceback (most recent call last):
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/gradio/queueing.py", line 706, in process_events
response = await route_utils.call_process_api(
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api
output = await app.get_blocks().process_api(
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/gradio/blocks.py", line 2018, in process_api
result = await self.call_function(
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/gradio/blocks.py", line 1579, in call_function
prediction = await utils.async_iteration(iterator)
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/gradio/utils.py", line 691, in async_iteration
return await anext(iterator)
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/gradio/utils.py", line 685, in anext
return await anyio.to_thread.run_sync(
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread
return await future
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 943, in run
result = context.run(func, *args)
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/gradio/utils.py", line 668, in run_sync_iterator_async
return next(iterator)
File "/data/wj/anaconda3/envs/videollm/lib/python3.10/site-packages/gradio/utils.py", line 829, in gen_wrapper
response = next(iterator)
File "/data/wj/videollm-online/demo/app.py", line 92, in gr_liveinfer_queue_refresher_change
query, response = liveinfer()
File "/data/wj/videollm-online/demo/inference.py", line 129, in call
query, response = self._call_for_response(video_time, query)
File "/data/wj/videollm-online/demo/inference.py", line 48, in _call_for_response
assert self.last_ids == 933, f'{self.last_ids} != 933' # HACK, 933 = ]\n
AssertionError: tensor([[0]], device='cuda:0') != 933

Could you please tell me what to do? Thanks a lot!
By the way, my cli.py is working fine.