Skip to main content
Search

Amir Mann

1 related articles

Subscribe to updates
  1. arXiv

    Diffusion language models stop waiting for a whole block to finish: B3 overlaps two blocks in one forward pass for 11.5–14.5% more throughput

    Block diffusion language models generate one block at a time, and a block cannot hand off until its slowest token settles, so compute idles at block tails. B3 initializes the next block once the current one is settled enough, denoises both in a shared forward pass, and calibrates the spawn point online from the model's own acceptance behavior, with no training or hyperparameter tuning. On DiffusionGemma 26B, LLaDA 2.1 mini 16B and flash 100B across 10 datasets, B3 raises tokens per second by 11.5–14.5% at on-par generation quality.

You’re all caught up