docker版本启动成功，提交prompt报错

[akfheaven]

root@3a73dd9b73dd:/data/shared/Qwen# python web_demo_mm.py --flash-attn2 --server-name 0.0.0.0
You are attempting to use Flash Attention 2.0 without specifying a torch dtype. This might lead to unexpected behaviour
Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████| 5/5 [04:30<00:00, 54.03s/it]
Some parameters are on the meta device because they were offloaded to the cpu.
Running on local URL: http://0.0.0.0:7860

To create a public link, set share=True in launch().
/usr/local/lib/python3.8/dist-packages/gradio/analytics.py:106: UserWarning: IMPORTANT: You are using gradio version 4.42.0, however version 4.44.1 is available, please upgrade.

warnings.warn(
User: 你是谁
Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/gradio/queueing.py", line 536, in process_events
response = await route_utils.call_process_api(
File "/usr/local/lib/python3.8/dist-packages/gradio/route_utils.py", line 321, in call_process_api
output = await app.get_blocks().process_api(
File "/usr/local/lib/python3.8/dist-packages/gradio/blocks.py", line 1935, in process_api
result = await self.call_function(
File "/usr/local/lib/python3.8/dist-packages/gradio/blocks.py", line 1532, in call_function
prediction = await utils.async_iteration(iterator)
File "/usr/local/lib/python3.8/dist-packages/gradio/utils.py", line 671, in async_iteration
return await iterator.anext()
File "/usr/local/lib/python3.8/dist-packages/gradio/utils.py", line 664, in anext
return await anyio.to_thread.run_sync(
File "/usr/local/lib/python3.8/dist-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "/usr/local/lib/python3.8/dist-packages/anyio/_backends/_asyncio.py", line 2177, in run_sync_in_worker_thread
return await future
File "/usr/local/lib/python3.8/dist-packages/anyio/_backends/_asyncio.py", line 859, in run
result = context.run(func, *args)
File "/usr/local/lib/python3.8/dist-packages/gradio/utils.py", line 647, in run_sync_iterator_async
return next(iterator)
File "/usr/local/lib/python3.8/dist-packages/gradio/utils.py", line 809, in gen_wrapper
response = next(iterator)
File "web_demo_mm.py", line 189, in predict
for response in call_local_model(model, processor, messages):
File "web_demo_mm.py", line 157, in call_local_model
for new_text in streamer:
File "/usr/local/lib/python3.8/dist-packages/transformers/generation/streamers.py", line 223, in next
value = self.text_queue.get(timeout=self.timeout)
File "/usr/lib/python3.8/queue.py", line 178, in get
raise Empty
_queue.Empty