Micron sedang membangunkan memori inferens tepi khusus untuk AI fizikal.

During the Korea Semiconductor Exhibition SEDEX 2026 held at COEX in Seoul, Micron Technology Vice President Lee Cheol revealed that the company is advancing the development of Edge Inference Memory (EIM) for physical AI; mass production of this product is expected to commence in the second half of 2028. To meet the urgent demand for low-power DRAM in fields such as autonomous driving and humanoid robots, Micron is exploring the integration of EIM into LPDDR6 and has already initiated in-depth discussions with key customers on this matter. According to the Science and Technology Innovation Board Daily, EIM is deployed between AI chips and memory, adopting a technical approach wherein LPDDR is directly stacked atop logic chips to enable high-speed processing of inference data; however, specific details regarding the current computing architecture have not yet been disclosed publicly. Lee Cheol noted that AI models currently used in robots contain approximately 1–2 billion parameters, resulting in relatively limited bandwidth pressure; however, as more advanced vision-language models are gradually deployed, reliance solely on conventional LPDDR will no longer suffice to meet their bandwidth requirements.