Just tried glid-3 with a batch size of one and I'm getting 4781MiB. The latent d... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

Jack000 on April 7, 2022 | parent | context | favorite | on: Dall-E 2

Just tried glid-3 with a batch size of one and I'm getting 4781MiB. The latent diffusion model peaks at 8403MiB

These are fp16 numbers though, you might need a recent nvidia card to run it.

rahimnathwani on April 7, 2022 [–]

I'll try them out. I have an RTX 2070, which apparently supports fp16. But it only has 8GB RAM.

I used the instructions here to check: https://github.com/wang-xinyu/tensorrtx/blob/master/tutorial...

Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact