Spaces:
Running
on
T4
Running
on
T4
Apply for community grant: Academic project (gpu)
#1
by
yuntian-deng
- opened
This demo implements my ICLR paper "Markup-to-Image Diffusion Models with Scheduled Sampling" (https://huggingface.co/papers/2210.05147), which converts LaTeX into formula images using diffusion models.
Initially, this demo ran on GPUs. Due to limited resources, it now runs on CPUs, causing much slower inference times.
I'm applying for complimentary GPU access (even a low-end Nvidia T4 would suffice) for two main reasons:
- Performance: Switching back to GPUs will make inference 10 times faster, greatly enhancing usability for users.
- Open Science Value: A high-performance demo enables researchers to more easily reproduce the results claimed by the paper.
Thank you for considering this application.
Hi @yuntian-deng , we have assigned a gpu to this space. Note that GPU Grants are provided temporarily and might be removed after some time if the usage is very low.
To learn more about GPUs in Spaces, please check out https://huggingface.co/docs/hub/spaces-gpus
Thank you!