LP-Spec: Leveraging LPDDR PIM for Efficient LLM Mobile Speculative Inference with Architecture-Dataflow Co-Optimization.
Siyuan He, Zhantong Zhu, Yandong He, Tianyu Jia
Browse the full ICCAD paper archive.
Siyuan He, Zhantong Zhu, Yandong He, Tianyu Jia
Browse the full ICCAD paper archive.