Live data from Hacker News

Block Diffusion: Interpolating between autoregressive and diffusion models

arxiv.org

1–10 of 37 posts

Re: Block Diffusion: Interpolating between autoregressive and diffusion models

#3
The memory bandwidth bottleneck limits the speed of running local models, the fact that this model is parallelizable means that even with one batch inference it will be possible to balance memory bandwidth bottleneck and compute bottleneck (aka much more speed).

Re: Block Diffusion: Interpolating between autoregressive and diffusion models

#10
Based on the animation, I personally don't expect this to be very helpful. The main way diffusion models help is preventing answers like "No. [proceeds to explain why the answer is yes]", and since the blocks are so small, the LLM can't fully explain before it has to say yes or no.
Post reply on HN