CSpace

浏览/检索结果: 共1条,第1-1条 帮助

已选(0)清除 条数/页:   排序方式:
Pyramid: Accelerating LLM Inference With Cross-Level Processing-in-Memory 期刊论文
IEEE COMPUTER ARCHITECTURE LETTERS, 2025, 卷号: 24, 期号: 1, 页码: 121-124
作者:  Yan, Liang;  Lu, Xiaoyang;  Chen, Xiaoming;  Han, Yinhe;  Sun, Xian-He
收藏  |  浏览/下载:1/0  |  提交时间:2025/06/25
Graphics processing units  Decoding  Computational modeling  Parallel processing  Systolic arrays  Computer architecture  Table lookup  Random access memory  Interpolation  Transformers  Large language models  Processing-in-memory