Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Uno pairs autoregressive LLMs with lightweight diffusion weights to draw multiple tokens in parallel, delivering up to 3x lossless speedup without a draft model.
1 stories, newest first · one card per story
Uno pairs autoregressive LLMs with lightweight diffusion weights to draw multiple tokens in parallel, delivering up to 3x lossless speedup without a draft model.
Today 1.6K readers · 2.4K views · 776 reads · all time 189K views