Hi everyone, I’m encountering an issue when running my code on Space using ZeroGPU. I’ve set .to("cuda") on the pipeline, but I can’t figure out what’s going wrong. Locally, with two A100 GPUs, everything works fine. Here is the complete error I’m getting: Traceback (most recent call last): F…

As it is a new creation, I think it will change. As a workaround, if you change the name of the currently existing space and create a new space in its place, you can achieve the same URL and keep the previous space without deleting it.

Issue with .to("cuda") on Space and ZeroGPU - RuntimeError: Expected all tensors to be on the same device

Spaces

system Closed November 11, 2024, 2:15pm 13

This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.

Topic		Replies	Views
Expected all tensors to be on the same device Beginners	3	9506	April 30, 2022
ZeroGPU issues: Assertion `srcIndex < srcSelectDimSize` failed Beginners	1	258	October 12, 2024
HF Space: RuntimeError: CUDA error: no kernel image is available for execution on the device Spaces	0	1709	October 26, 2022
Error while initializing ZeroGPU Models	13	279	August 10, 2025
Unable to use ZeroGPU/T4 in spaces on tensorflow model Spaces	3	71	September 9, 2024

Issue with .to("cuda") on Space and ZeroGPU - RuntimeError: Expected all tensors to be on the same device

Related topics