HuggingFace - RuntimeError

[lucellent]

When I try to run the inference there it just shows a red box with RuntimeError, nothing else (after loading for a minute)

[yhliu04]

@lucellent Since the inference time will exceed the ZeroGPU limitation, you could try to duplicate the code and run with a paid GPU (e.g. L4, A100, …)

[lucellent]

I rented ZeroGPU but still am unable to run it.

ZeroGPU tensors packing: 0.00B [00:00, ?B/s]
ZeroGPU tensors packing: 0.00B [00:00, ?B/s]

• Running on local URL: http://0.0.0.0:7860, with SSR ⚡
  Attempted to select a non-interactive or hidden tab.
  Attempted to select a non-interactive or hidden tab.

To create a public link, set share=True in launch().
Attempted to select a non-interactive or hidden tab.
Attempted to select a non-interactive or hidden tab.
2025-01-31 12:03:46,326 - video_to_video - INFO - checkpoint_path: ./pretrained_weight

open_clip_pytorch_model.bin: 0%| | 0.00/3.94G [00:00<?, ?B/s]
open_clip_pytorch_model.bin: 1%|▏ | 52.4M/3.94G [00:01<01:15, 51.2MB/s]
open_clip_pytorch_model.bin: 27%|██▋ | 1.08G/3.94G [00:02<00:04, 619MB/s]
open_clip_pytorch_model.bin: 53%|█████▎ | 2.11G/3.94G [00:03<00:02, 803MB/s]
open_clip_pytorch_model.bin: 83%|████████▎ | 3.26G/3.94G [00:04<00:00, 940MB/s]
open_clip_pytorch_model.bin: 100%|█████████▉| 3.94G/3.94G [00:05<00:00, 738MB/s]
2025-01-31 12:04:04,695 - video_to_video - INFO - Build encoder with FrozenOpenCLIPEmbedder
Model not found at ./pretrained_weight, downloading...
Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 622, in process_events
response = await route_utils.call_process_api(
File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 323, in call_process_api
output = await app.get_blocks().process_api(
File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2016, in process_api
result = await self.call_function(
File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1569, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
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 2461, in run_sync_in_worker_thread
return await future
File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 962, in run
result = context.run(func, *args)
File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 846, in wrapper
response = f(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/spaces/zero/wrappers.py", line 210, in gradio_handler
raise error("ZeroGPU worker error", "GPU task aborted")
gradio.exceptions.Error: 'GPU task aborted'

[lucellent]

@yhliu04 Any idea if this is something from my side?