DFlash
DFlash is a speculative decoding method in which the draft model is a small block-diffusion network rather than an autoregressive one.
Explore Diffusion Models through related topics and the articles other pages reference most.
Articles that also belong to these categories. Counts cover all of Diffusion Models.
Showing 1-1 of 1 article
DFlash is a speculative decoding method in which the draft model is a small block-diffusion network rather than an autoregressive one.