机器上有两张卡，启动一直报错

[kangkang721]

Note that the issue tracker is NOT the place for general support.
2024-06-13 06:06:31,034 xinference.core.supervisor 63 INFO Xinference supervisor 0.0.0.0:13602 started
2024-06-13 06:06:35,130 xinference.core.worker 63 INFO Starting metrics export server at 0.0.0.0:None
2024-06-13 06:06:35,133 xinference.core.worker 63 INFO Checking metrics export server...
2024-06-13 06:06:36,778 xinference.core.worker 63 INFO Metrics server is started at: http://0.0.0.0:40018
2024-06-13 06:06:36,779 xinference.core.worker 63 INFO Xinference worker 0.0.0.0:13602 started
2024-06-13 06:06:36,780 xinference.core.worker 63 INFO Purge cache directory: /root/.xinference/cache
2024-06-13 06:06:38,294 xinference.api.restful_api 1 INFO Starting Xinference at endpoint: http://0.0.0.0:9997
2024-06-13 06:06:38,782 xinference.core.worker 63 ERROR Report status got error.
Traceback (most recent call last):
File "/opt/conda/lib/python3.10/site-packages/xinference/core/worker.py", line 762, in report_status
status = await asyncio.to_thread(gather_node_info)
File "/opt/conda/lib/python3.10/asyncio/threads.py", line 25, in to_thread
return await loop.run_in_executor(None, func_call)
asyncio.exceptions.CancelledError

During handling of the above exception, another exception occurred:

[codingl2k1]

一张卡时没问题吗？你用的什么版本xinference？

[Modas-Li]

same issue, did you solve it?

[github-actions]

This issue is stale because it has been open for 7 days with no activity.