9 papers
HiSpec: Hierarchical Speculative Decoding for LLMs
Avinash Kumar, Sujay Sanghavi, Poulami Das
Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. ve…
Transpiler-Architecture Co-Design to Curb Clifford Costs in Fault-Tolerant Quantum Computing
Meng Wang, Chenxu Liu, Samuel Stein +4
Quantum Error Correction (QEC) codes form the foundation of Fault-Tolerant Quantum Computing (FTQC) and predominantly use the Clifford+T gate set. Recently, Clifford operations hav…
ATHENA: A Compiler For Optimized Scheduling In Distributed Quantum Computers
Won Joon Yun, Dhilan Nag, Sneha Ballabh +3
Distributed Quantum Computers (DQCs) enable large system sizes by connecting smaller chips via photonic interconnects. DQCs use teleportation to relocate qubits and execute CNOTs b…
GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems
Sourish Wawdhane, Avinash Kumar, Poulami Das
Mixture-of-Expert (MoE) models enable efficient inference by employing smaller experts and activating only a subset of them per token. MoE serving engines distribute experts across…
Test-Time Speculation
Avinash Kumar, Sujay Sanghavi, Poulami Das
Speculative decoding accelerates LLM inference by using a fast draft model to generate tokens and a more accurate target model to verify them. Its performance depends on the $\text…
Are LLMs Good For Quantum Software, Architecture, and System Design?
Sourish Wawdhane, Poulami Das
Quantum computers promise massive computational speedup for problems in many critical domains, such as physics, chemistry, cryptanalysis, healthcare, etc. However, despite decades…