Issue: OSError: [Errno 28] No space left on device despite choosing 150GB persistent storage

#141
by LTT - opened

ZeroGPU tensors packing: 0%| | 0.00/66.4G [00:00<?, ?B/s]
ZeroGPU tensors packing: 0%| | 0.00/66.4G [00:01<?, ?B/s]
Traceback (most recent call last):
File "/home/user/app/app.py", line 490, in
main()
File "/home/user/app/app.py", line 486, in main
demo.launch()
File "/usr/local/lib/python3.10/site-packages/spaces/zero/gradio.py", line 142, in launch
task(*task_args, **task_kwargs)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/patching.py", line 344, in pack
_pack(Config.zerogpu_offload_dir)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/patching.py", line 336, in _pack
pack = pack_tensors(originals, fakes, offload_dir, callback=update)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/torch/packing.py", line 114, in pack_tensors
os.posix_fallocate(fd, 0, total_asize)
OSError: [Errno 28] No space left on device

image.png

I am encountering an issue where I have already selected the 150GB paid persistent storage option for my Hugging Face Space. However, during the ZeroGPU tensors packing process, the code uses approximately 66.4GB of space and raises the error, Could you clarify why this error is occurring even though there should be sufficient storage space available? Is there a limitation or configuration step I might have missed? Any guidance on resolving this issue would be appreciated.

Sign up or log in to comment