The AMD ecosystem finally has a competitive diffusion language model, how much computing power did TiDAR save with this move?

View Original
MeNews
Zyphra releases the first diffusion language model in the AMD ecosystem, achieving a maximum speedup of 7.7 times
Zyphra releases ZAYA1-8B-Diffusion-Preview, transforming autoregressive large language models into hybrid expert diffusion models, becoming the first diffusion language model trained within the AMD hardware ecosystem. By using TiDAR to skip from-scratch pretraining, it can denoise 16 tokens simultaneously in a single forward pass, turning memory bottlenecks into compute bottlenecks. Empirical tests show a 4.6x acceleration with CCA attention + lossless sampling, increasing to 7.7x after switching to the hybrid logit sampler.
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned