Scholarlink

<p>Transformer networks, driven by self-attention, are central to large language models. In generative transformers, self-attention uses cache memory to store token projections, avoiding recomputation at each time step. However, graphics processing unit (GPU)-stored projections must be loaded into static random-access memory for each new generation step, causing latency and energy bottlenecks. Here we present a custom self-attention in-memory computing architecture based on emerging charge-based memories called gain cells, which can be efficiently written to store new tokens during sequence generation and enable parallel analog dot-product computation required for self-attention. However, the analog gain-cell circuits introduce non-idealities and constraints preventing the direct mapping of pre-trained models. To circumvent this problem, we design an initialization algorithm achieving text-processing performance comparable to GPT-2 without training from scratch. Our architecture reduces attention latency and energy consumption by up to two and four orders of magnitude, respectively, compared with GPUs, marking a substantial step toward ultrafast, low-power generative transformers.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analog in-memory computing attention mechanism for fast and energy-efficient large language models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月8日

查看全文
  • Nathan Leroux,
  • Paul-Philipp Manea,
  • Chirag Sudarshan,
  • Jan Finkbeiner,
  • Sebastian Siegel,
  • John Paul Strachan,
  • Emre Neftci

摘要

Transformer networks, driven by self-attention, are central to large language models. In generative transformers, self-attention uses cache memory to store token projections, avoiding recomputation at each time step. However, graphics processing unit (GPU)-stored projections must be loaded into static random-access memory for each new generation step, causing latency and energy bottlenecks. Here we present a custom self-attention in-memory computing architecture based on emerging charge-based memories called gain cells, which can be efficiently written to store new tokens during sequence generation and enable parallel analog dot-product computation required for self-attention. However, the analog gain-cell circuits introduce non-idealities and constraints preventing the direct mapping of pre-trained models. To circumvent this problem, we design an initialization algorithm achieving text-processing performance comparable to GPT-2 without training from scratch. Our architecture reduces attention latency and energy consumption by up to two and four orders of magnitude, respectively, compared with GPUs, marking a substantial step toward ultrafast, low-power generative transformers.