Heterogeneous Integration on Organic Interposer Substrate with fine-pitch RDL and 40 micron pitch Micro-bumpsKatsuyuki SakumaGriselda Bonillaet al.2023ECTC 2023
RaPiD: AI Accelerator for Ultra-Low Precision Training and InferenceSwagath VenkataramaniVijayalakshmi Srinivasanet al.2021ISCA 2021
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training Chia-Yu ChenJiamin Niet al.2020NeurIPS 2020
Cryogenic Analog 1T-ReRAM with Enhanced Dynamic Range and Suppressed Noise for Cold Neural NetworksSaketh Ram MamidalaDavide Lombardoet al.2024IEDM 2024
A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-ExpertsMohammed Nowaz Rabbani ChowdhuryMeng Wanget al.2024ICML 2024
Analog AI as a Service: A Cloud Platform for In-Memory ComputingKaoutar El MaghraouiKim Tranet al.2024SSE 2024
Securing AI Inference in the Cloud: Is CPU-GPU Confidential Computing Ready ?Apoorve MohanMengmei Yeet al.2024CLOUD 2024