Mercury 3: How Inception Labs Scaled Diffusion LLMs to 1,000 Tokens Per Second
This story is from 2026-10-28. It is preserved in the archive; the latest stories are on the live feed.
Mercury 3: How Inception Labs Scaled Diffusion LLMs to 1,000 Tokens Per Second When most people think of large language models, they picture the same basic loop: generate one token, append it to the context, generate the next. Autoregressive decoding has been the default for years, and for good rea…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-28 16:04 · DEV Community — Machine Learning
Mercury 3: How Inception Labs Scaled Diffusion LLMs to 1,000 Tokens Per Second