Spaces:
Running
Error initializing ZeroGPU: Unknown
Hey, i see that since yesterday when you try to make a zerogpu space or duplicate one, i get an error similar to this everytime:
Traceback (most recent call last):
File "/home/user/app/app.py", line 45, in <module>
def generate_arena_images(
File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 113, in _GPU
client.startup_report()
File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 45, in startup_report
raise RuntimeError("Error while initializing ZeroGPU: Unknown")
RuntimeError: Error while initializing ZeroGPU: Unknown
It fixes by literally factory rebuild over and over again the space till it works, even if it takes alot of time and i hope its just a temporary problem.
Is it only me or others too?
I also encounter this problem. Don't know what happens. I hope they can fix it soon.
Hey for me you just have to import spaces and then write @space .GPU in you'r code
Yup in the code there is @spaces.GPU(), as i said i also tried duplicating any zerogpu space, and it happens, sometimes doesnt but most of the times for me it does
I think there are some problems with the zerogpu api, as for example in my space https://huggingface.co/spaces/Nick088/Stable_Diffusion_Finetuned_Minecraft_Skin_Generator when i click submit, i get:
Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 532, in process_events
response = await route_utils.call_process_api(
File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 276, in call_process_api
output = await app.get_blocks().process_api(
File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1923, in process_api
result = await self.call_function(
File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1509, in call_function
prediction = await anyio.to_thread.run_sync(
File "/usr/local/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 "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2177, in run_sync_in_worker_thread
return await future
File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 859, in run
result = context.run(func, *args)
File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 832, in wrapper
response = f(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 144, in gradio_handler
schedule_response = client.schedule(task_id=task_id, request=request, duration=duration)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 121, in schedule
raise RuntimeError(f"ZeroGPU API /schedule error: {res} ({httpx.codes.get_reason_phrase(res)})") # pragma: no cover
RuntimeError: ZeroGPU API /schedule error: 500 (Internal Server Error)
when it worked all fine some days ago
EDIT: Seems like just factory rebuilding it makes it work i guess?
Seems like this was an API error that got fixed by now, so im going to close this discussion