Published at 10/19/2026, 8:06:55 PM · 58 views
📰 Inception Unveils Mercury 3: Diffusion-Based LLM Breaks 1,000+ Tok/s with 1M Context Window
Inception co-founder Stefano Ermon officially unveiled Mercury 3, the company's next-generation diffusion-based large language model. Delivering an astonishing 1,068 tokens per second inference speed on NVIDIA GPUs, Mercury 3 scales to 40x the size of Mercury 1 with a native 1M context window.
💬 What's your take? Join the discussion in the comments.
Read the original Chinese version
📰 Inception 正式发布 Mercury 3：扩散架构大模型突破 1000 Token/s，100 万上下文挑战 GPT-6 与 Haiku
前沿 AI 初创公司 Inception 联合创始人 Stefano Ermon 宣布正式推出新一代扩散架构大语言模型 Mercury 3。模型在 NVIDIA GPU 上实现高达 1,068 Token/秒的超高生成吞吐，参数量达到前代 Mercury 1 的 40 倍并支持 100 万（1M）Token…
💬 你怎么看？欢迎在评论区讨论。
#Inception #Mercury 3 #Diffusion LLM
0 Comments