# Issue with space zerogpu

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-space-zerogpu%2F178702%3E%5C
**Category:** Spaces\
**Created:** [August 15, 2026, 9:20am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-space-zerogpu%2F178702 "2026-08-15T09:20:05Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![dayona](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/dayona/32/62391_2.png) [@dayona](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdayona)%5C
**Post date:** [August 15, 2026, 9:20am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-space-zerogpu%2F178702%2F1 "2026-08-15T09:20:05Z")

</div>

Hi HF Team & Community,

I just created a new Space using ZeroGPU, but the application keeps crashing and restarting right after initialization.

ZeroGPU tensors packing: 100%|██████████| 6.94G/6.94G [00:03\<00:00, 1.80GB/s]

- Running on local URL: [http://0.0.0.0:7860](http://0.0.0.0:7860)  
=== Application restarted at … ===

[https://huggingface.co/posts/dayona/348313462034493](https://huggingface.co/posts/dayona/348313462034493)

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [August 15, 2026, 8:19pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-space-zerogpu%2F178702%2F3 "2026-08-15T20:19:57Z")

</div>

Yeah. Maybe fixed by HF: [Spaces aren't allocating for ZeroGPU tonight - #10 by hysts](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fspaces-arent-allocating-for-zerogpu-tonight%2F178683%2F10)

Edit:  
If it still isn’t fixed, I think there might be a different cause. If you’re hesitant to share the code, maybe just showing me the code around where Gradio crashed would help me troubleshoot the issue…