Spaces:
Running
⚡ ZeroGPU: New version rolled out! (sept 2024)
Hello everybody,
We've rolled out a major update to ZeroGPU! All the Spaces are now running on it.
Major improvements:
- GPU cold starts about twice as fast!
- RAM usage reduced by two-thirds, allowing more effective resource usage, meaning more GPUs for the community!
- ZeroGPU initializations (coldstarts) can now be tracked and displayed (use
progress=gr.Progress(track_tqdm=True)) - Improved compatibility and PyTorch integration, increasing ZeroGPU compatible spaces without requiring any modifications!
Feel free to answer in this discussion if you have any questions!
🤗 Best regards,
Charles
Hi, Charles!
No limit reset time is now displayed (to get more quotas or retry in 1:35:47)?
Hi Charles.
The results from ZeroGPU differ from those on my local machine / Hugging Face's L4 GPU, even with the same code and Python dependencies.
For more information, visit: https://huggingface.co/spaces/zero-gpu-explorers/README/discussions/111
Hi.
I found a very strange behavior. It is hard to find and would never happen locally. Maybe it is related to the bug above.
https://huggingface.co/spaces/zero-gpu-explorers/README/discussions/104#66f66a4b693f423f5b6d9b2e
Apparently, this time the behavior of Gradio's Cancel task is wrong. If it is bad, it may be a problem with Queue in general.
https://huggingface.co/spaces/zero-gpu-explorers/README/discussions/113#66fbc59085944df7944ff4aa
Hi @cbensimon !
Is there an example of how to show cold-start time to users as mentioned here?:
ZeroGPU initializations (coldstarts) can now be tracked and displayed (use progress=gr.Progress(track_tqdm=True))
In my Zero GPU code, I assumed this meant to add it to the spaces.GPU decorator as
@spaces.GPU(duration=40, progress=gr.Progress(track_tqdm=True))
But I'm not seeing any visual indicator! There's no error thrown, but also no difference with that arg on or off, so not quite sure what I need to change! Thank you for your help!
(Code here if it helps: https://huggingface.co/spaces/WillHeld/diva-audio-chat/blob/main/app.py#L61)
I have heard that nest-asyncio, which is newly starting to be used in the spaces library, has quite a few problems around memory management.
I would like the library authors to find another alternative if possible.
I found that my model inference is much slower (~ x5 slower) running on zeroGPU than on my local GPU (V100, 16GB). May I know if there is a way to speed it up?