31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding

Pingcheng Dong, Yonghao Tan, Xuejiao Liu, Peng Luo, Yu Liu, Di Pang, Songchen Ma, Xijie Huang, Shih-Yang Liu, Dong Zhang, Zhichao Lu, Luhong Liang, Chi-Ying Tsui, Fengbin Tu, Liang Zhao, Kwang-Ting Cheng

BibTeX
@inproceedings{dong2026token,
  author = {Pingcheng Dong and Yonghao Tan and Xuejiao Liu and Peng Luo and Yu Liu and Di Pang and Songchen Ma and Xijie Huang and Shih-Yang Liu and Dong Zhang and Zhichao Lu and Luhong Liang and Chi-Ying Tsui and Fengbin Tu and Liang Zhao and Kwang-Ting Cheng},
  title = {{31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding}},
  booktitle = {ISSCC},
  year = {2026},
  doi = {10.1109/isscc49663.2026.11409211},
}

Loading related content...

Figure