2 papers
cs.LG2026
Mira: Memory-Efficient MoE Inference Using Adaptive Caching and Predictive Expert Staging
Sanjali Yadav, Bahar Asgari
Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-constrained, single-GPU syste…
cs.LG2024
Misam: Using ML in Dataflow Selection of Sparse-Sparse Matrix Multiplication
Sanjali Yadav, Bahar Asgari
Sparse matrix-matrix multiplication (SpGEMM) is a critical operation in numerous fields, including scientific computing, graph analytics, and deep learning. These applications expl…