When i try to use ZeroGPU, it keeps saying "GPU Task aborted""

Beginners
1

when i try to do something using ZeroGPU with @spaces.GPU it keeps giving me an error saying “GPU Task aborted”

1 Like
2

A little more detail, please. If it’s a usage issue, someone can advise. Note that there was a bug with the same symptoms recently, but I think it has been fixed about 70% of the time.

3

i made a space, GGUF Playground, but when i call the function to generate a response, it gives me an error saying “GPU Task aborted”, these are the logs:
Traceback (most recent call last):
File “/usr/local/lib/python3.10/site-packages/gradio/queueing.py”, line 536, in process_events
response = await route_utils.call_process_api(
File “/usr/local/lib/python3.10/site-packages/gradio/route_utils.py”, line 322, in call_process_api
output = await app.get_blocks().process_api(
File “/usr/local/lib/python3.10/site-packages/gradio/blocks.py”, line 1935, in process_api
result = await self.call_function(
File “/usr/local/lib/python3.10/site-packages/gradio/blocks.py”, line 1532, in call_function
prediction = await utils.async_iteration(iterator)
File “/usr/local/lib/python3.10/site-packages/gradio/utils.py”, line 671, in async_iteration
return await iterator.anext()
File “/usr/local/lib/python3.10/site-packages/gradio/utils.py”, line 776, in asyncgen_wrapper
response = await iterator.anext()
File “/usr/local/lib/python3.10/site-packages/gradio/chat_interface.py”, line 653, in _stream_fn
first_response = await async_iteration(generator)
File “/usr/local/lib/python3.10/site-packages/gradio/utils.py”, line 671, in async_iteration
return await iterator.anext()
File “/usr/local/lib/python3.10/site-packages/gradio/utils.py”, line 664, in anext
return 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 647, in run_sync_iterator_async
return next(iterator)
File “/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py”, line 354, in gradio_handler
raise gr.Error(“GPU task aborted”)
gradio.exceptions.Error: ‘GPU task aborted’

4

I now duplicated this and it worked normally… any changes?

Sorry. No, it’s not. There’s an error in the original, too. It’s buggy, though it’s still up and running.

5

So I fixed the bug. Try duplicating it on your Zero GPU space. It should work.

6

you can delete the space now, i already accepted the pull request you made, anyways, thank you

7

Deleted. It works, it’s fine.

8

The same happens to me. I have an space in ZeroGPU and it happens constantly but now always. And that is the annoying part because I cant replay the error because it happens sporadically, not always, without changinf any line of code.

2 Likes
9

Same for me but I’ve been having it everytime.
I’ve created another space just to debug, and I’ve used a very simple pipeline using Llama 3.1 8b Instruct, a simple text placeholder and an output text.
I’ve decorated my ‘generate_text’ function but still, I get the ‘GPU task aborted’ error after a dozen of seconds (even with a duration set in the decorator).

I can’t make the troubleshooting code more simple, yet I still get the error. Anyone understands the issue ?
Thank you a lot

3 Likes