DiffusionGemma：Google 基于扩散模型的文本生成新方案DiffusionGemma
Google 去年曾短暂发布实验性的 Gemini Diffusion 模型，预览阶段实测速度达到 857 tokens/秒，但随后再无消息。如今该研究以 DiffusionGemma 之名回归，将扩散模型架构应用于文本生成任务。这标志着 Google 在非自回归文本生成路线上的持续投入。DiffusionGemma 有望为高速文本推理提供新的技术路径。
Simon Willison
10th June 2026 - Link Blog
DiffusionGemma (via) Last May Google briefly released an experimental Gemini Diffusion model. I tried the preview at the time and recorded it running at 857 tokens/second. It was an exciting model, but Google made no further announcements about it.
That research has returned in the best possible way: as a new open weight (Apache 2 licensed) Gemma model, google/diffusiongemma-26B-A4B-it.
NVIDIA are currently hosting the model for free on their NIM cloud API. I used that API to generate this pelican, which took 4.4s (according to time uv run generate.py) to return 2,409 tokens - so at least 500 tokens/second.
Posted 10th June 2026 at 8 pm
Recent articles
This is a link post by Simon Willison, posted on 10th June 2026.
google 411 ai 2,066 generative-ai 1,824 llms 1,792 nvidia 18 pelican-riding-a-bicycle 118 gemma 15 llm-release 205 llm-performance 16
Monthly briefing
Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.
Pay me to send you less!
需要完整排版与评论请前往来源站点阅读。