3 citations · 6 across the 5 of their papers we have counts for
5 papers · 1 filter
Glinthawk: A Two-Tiered Architecture for Offline LLM Inference
Pouya Hamadanian, Sadjad Fouladi
We introduce Glinthawk, an architecture for offline Large Language Model (LLM) inference. By leveraging a two-tiered structure, Glinthawk optimizes the utilization of the high-end…
Online Reinforcement Learning in Non-Stationary Context-Driven Environments
Pouya Hamadanian, Arash Nasr-Esfahany, Malte Schwarzkopf +2
We study online reinforcement learning (RL) in non-stationary environments, where a time-varying exogenous context process affects the environment dynamics. Online RL is challengin…
Demystifying Reinforcement Learning in Time-Varying Systems
Pouya Hamadanian, Malte Schwarzkopf, Siddartha Sen +1
Recent research has turned to Reinforcement Learning (RL) to solve challenging decision problems, as an alternative to hand-tuned heuristics. RL can learn good policies without the…
CausalSim: A Causal Framework for Unbiased Trace-Driven Simulation
Abdullah Alomar, Pouya Hamadanian, Arash Nasr-Esfahany +3
We present CausalSim, a causal framework for unbiased trace-driven simulation. Current trace-driven simulators assume that the interventions being simulated (e.g., a new algorithm)…
Real-Time Video Inference on Edge Devices via Adaptive Model Streaming
Mehrdad Khani, Pouya Hamadanian, Arash Nasr-Esfahany +1
Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks. We present Adaptive Model Streaming…