Serverless Pod Disk Space Issue with Large Model (FLUX.1-schnell)

I'm trying to deploy a Hugging Face diffusion model (black-forest-labs/FLUX.1-schnell) on a serverless GPU endpoint, but I'm running into a "No space left on device" error during model download. Even though I selected 100GB storage volume, logs show that only ~5GB disk space is being used, and downloads fail due to lack of space. 1. Why isn't the full 100GB volume being used? 2. How can I redirect Hugging Face cache to the mounted volume to avoid this issue? 3. Is serverless not suitable for large diffusion models like FLUX.1-schnell? Any advice or workaround would be appreciated. Thanks!
1 Reply
Unknown User
Unknown User5mo ago
Message Not Public
Sign In & Join Server To View

Did you find this page helpful?