collaborators

6 papers

cs.CL2026

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…

cs.DC2026

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…

cs.CL2026

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…

cs.CL2025

HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving

Avinash Kumar, Shashank Nag, Jason Clemons +2

Early-Exit Large Language Models (EE-LLMs) enable high throughput inference by allowing tokens to exit early at intermediate layers. However, their throughput is limited by the com…

cs.CL2025

Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs

Ravi Ghadia, Avinash Kumar, Gaurav Jain +2

Autoregressive Transformers rely on Key-Value (KV) caching to accelerate inference. However, the linear growth of the KV cache with context length leads to excessive memory consump…

cs.CR2025

Context Switching for Secure Multi-programming of Near-Term Quantum Computers

Avinash Kumar, Meng Wang, Chenxu Liu +3

Multi-programming quantum computers improve device utilization and throughput. However, crosstalk from concurrent two-qubit CNOT gates poses security risks, compromising the fideli…