Ex. AMD Research Engineer, RT & Neural Rendering
2021 Graduate, Computer Graphics Group @ University of Tokyo.
https://aaryaman.net
The 16 cores of Strix halo helped a lot with compilation times, and PyTorch runs nicely too!
10.5 it/s on the default sd1.5 workflow with `python main.py --use-pytorch-cross-attention`
Wheels available - made with @scotttsai.bsky.social - see next post
The 16 cores of Strix halo helped a lot with compilation times, and PyTorch runs nicely too!
10.5 it/s on the default sd1.5 workflow with `python main.py --use-pytorch-cross-attention`
Wheels available - made with @scotttsai.bsky.social - see next post
10.5 it/s on the default sd1.5 workflow with `python main.py --use-pytorch-cross-attention`
Wheels available - made with @scotttsai.bsky.social - see next post
Jensen (Jinghao)Zhou, Hang Gao, Vikram Voleti, @adyaman.bsky.social, Chun-Han Yao, @markboss.bsky.social, @philiptorr.bsky.social, Christian Rupprecht, Varun Jampani
arxiv.org/abs/2503.14489
Jensen (Jinghao)Zhou, Hang Gao, Vikram Voleti, @adyaman.bsky.social, Chun-Han Yao, @markboss.bsky.social, @philiptorr.bsky.social, Christian Rupprecht, Varun Jampani
arxiv.org/abs/2503.14489