Memory-efficient Diffusion Transformers with Quanto and Diffusers

[sayakpaul]

With larger and larger diffusion transformers coming up, it's becoming increasingly important to have some good quantization tools for them.

We present our findings from a series of experiments on quantizing different diffusion pipelines based on diffusion transformers.

We demonstrate excellent memory savings with a bit of sacrifice on inference latency which is expected to improve in the coming days.

Diffusers 🤝 Quanto ❤️

Check out the blog post to know more:
https://huggingface.co/blog/quanto-diffusers