3 papers
cs.CL2025
RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
Payman Behnam, Yaosheng Fu, Ritchie Zhao +3
Transformer-based Large Language Models rely critically on the KV cache to efficiently handle extended contexts during the decode phase. Yet, the size of the KV cache grows proport…
eess.SP2024
Real-time Digital RF Emulation -- II: A Near Memory Custom Accelerator
Mandovi Mukherjee, Xiangyu Mao, Nael Rahman +16
A near memory hardware accelerator, based on a novel direct path computational model, for real-time emulation of radio frequency systems is demonstrated. Our evaluation of hardware…
cs.LG2023
STRIDE: Structure and Embedding Distillation with Attention for Graph Neural Networks
Anshul Ahluwalia, Payman Behnam, Rohit Das +4
Recent advancements in Graph Neural Networks (GNNs) have led to increased model sizes to enhance their capacity and accuracy. Such large models incur high memory usage, latency, an…