5 citations · 7 across the 3 of their papers we have counts for
3 papers
cs.LG2024★ 2 cited
CHAI: Clustered Head Attention for Efficient LLM Inference
Saurabh Agarwal, Bilge Acun, Basil Hosmer +5
Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute…
cs.DC2023★ 5 cited
Carbon Responder: Coordinating Demand Response for the Datacenter Fleet
Jiali Xing, Bilge Acun, Aditya Sundarrajan +5
The increasing integration of renewable energy sources results in fluctuations in carbon intensity throughout the day. To mitigate their carbon footprint, datacenters can implement…
cs.AR2023
MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendation
Samuel Hsia, Udit Gupta, Bilge Acun +5
Deep learning recommendation systems serve personalized content under diverse tail-latency targets and input-query loads. In order to do so, state-of-the-art recommendation models…