Consistency diffusion language models: Up to 14x faster, no quality loss

Re:Consistency diffusion language models: Up to 14x faster, ... by spockz on Friday February 20, 2026 @05:24AM (#47086108)

You can run smaller models on smaller compute hardware and split the compute. For large models you need to be able to fit the whole model in memory to get any decent throughput.

[ Parent | on HN ]

Re:Consistency diffusion language models: Up to 14x faster, ... by stavros on Friday February 20, 2026 @05:36AM (#47086213)

Ah interesting, I didn't realize MoE doesn't need to all run in the same place.

[ Parent | on HN ]