Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions docs/hub/spaces-zerogpu.md
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,8 @@ Unlike traditional single-GPU allocations, ZeroGPU's efficient system lowers bar

## Technical Specifications

- **GPU Type**: Nvidia A100
- **Available VRAM**: 40GB per workload
- **GPU Type**: Nvidia H200 slice
Copy link
Member

@julien-c julien-c Apr 29, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

there's (at least) one another mention of A100 above in the page

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

also: what is a slice? can you explain succintly what it means?

- **Available VRAM**: 70GB per workload

## Compatibility

Expand All @@ -34,7 +34,7 @@ ZeroGPU Spaces are designed to be compatible with most PyTorch-based GPU Spaces.
### Supported Versions

- Gradio: 4+
- PyTorch: 2.0.1, 2.1.2, 2.2.2, 2.4.0 (Note: 2.3.x is not supported due to a [PyTorch bug](https://github.com/pytorch/pytorch/issues/122085))
- PyTorch: 2.1.2, 2.2.2, 2.4.0, 2.5.1 (Note: 2.3.x is not supported due to a [PyTorch bug](https://github.com/pytorch/pytorch/issues/122085))
- Python: 3.10.13

## Getting started with ZeroGPU
Expand Down