核心信息
Inception AI 的 Mercury 2.5 现已通过 OpenRouter 全面上线,在无需专用硬件的模型中位居“最快模型”排行榜第一。
要点
- 这是一款基于扩散架构的大语言模型,能够并行解码 token,而非逐个生成,在代码密集型提示上提速最明显。
- 现已于 OpenRouter 上线,无需专用硬件,使用常规环境即可访问。
Inception AI 的 Mercury 2.5 现已通过 OpenRouter 全面上线,在无需专用硬件的模型中位居“最快模型”排行榜第一。
Mercury 2.5 from @_inception_ai is now generally available on OpenRouter. It's the fastest model on our Fastest Models leaderboard that doesn't require specialized hardware. A diffusion LLM: it decodes tokens in parallel rather than one at a time. The gain is largest on code-heavy prompts. Use it here: https://t.co/xTId0uFKC8