81 citations · 150 across the 48 of their papers we have counts for
5 papers · 1 filter
CRAFT: Fine-Grained Cost-Aware Expert Replication For Efficient Mixture-of-Experts Serving
Adrian Zhao, Zhenkun Cai, Zhenyu Song +5
Mixture-of-Experts (MoE) has recently emerged as the mainstream architecture for efficiently scaling large language models while maintaining near-constant computational cost. Exper…
Enhancing Programmability, Portability, and Performance with Rich Cross-Layer Abstractions
Nandita Vijaykumar
Programmability, performance portability, and resource efficiency have emerged as critical challenges in harnessing complex and diverse architectures today to obtain high performan…
SMASH: Co-designing Software Compression and Hardware-Accelerated Indexing for Efficient Sparse Matrix Operations
Konstantinos Kanellopoulos, Nandita Vijaykumar, Christina Giannoula +6
Important workloads, such as machine learning and graph analytics applications, heavily involve sparse linear algebra operations. These operations use sparse matrix compression as…
Decoupling GPU Programming Models from Resource Management for Enhanced Programming Ease, Portability, and Performance
Nandita Vijaykumar, Kevin Hsieh, Gennady Pekhimenko +6
The application resource specification--a static specification of several parameters such as the number of threads and the scratchpad memory usage per thread block--forms a critica…
Zorua: Enhancing Programming Ease, Portability, and Performance in GPUs by Decoupling Programming Models from Resource Management
Nandita Vijaykumar, Kevin Hsieh, Gennady Pekhimenko +5
The application resource specification--a static specification of several parameters such as the number of threads and the scratchpad memory usage per thread block--forms a critica…