Industry

Fractile AI 把 DRAM 直接堆叠在处理器上提升内存带宽

Why we picked it

这家叫 Fractile AI 的公司把内存直接焊在芯片上,专治大模型推理时带宽不够的老问题,还拉了头部实验室一起搞。做推理部署或关心算力成本的朋友可以看看这条路线。

Fractile AI 正在开发一种新的 AI 芯片架构,核心做法是把 DRAM 直接堆叠在处理器之上,用来满足前沿 AI 模型对内存带宽的需求。这一方案与市面上许多渐进式改良的芯片设计不同,属于对硬件堆叠方式的直接重构。

Body

根据投资人 Sara 的表述,Fractile AI 与多家头部实验室保持紧密合作来推进这一架构。其押注的逻辑是:当前大模型推理的主要瓶颈之一在于数据在内存与计算单元之间的搬运速度,而堆叠 DRAM 可以缩短数据通路、提高带宽。

在 GPU 之外,AI 芯片赛道涌现了大量创业公司,多数选择在现有架构上做增量优化,Fractile AI 则押注内存与计算一体化这条更激进的路线。

Original · Sarah Guo

1/ Excited for @goodwin_ml and team @fractile_ai. In a sea of incremental chip bets, they’re taking a huge swing (in close partnership with some of the top labs): stacking DRAM directly on top of the processor to support the memory bandwidth needs of frontier AI models

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Industry" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Fractile AI, AI芯片, 内存带宽, 推理硬件.

Source attribution: curated from Sarah Guo (@saranormous).