collaborators

5 papers

cs.LG2026

Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding

Rahul Thomas, Teo Kitanovski, Micah Goldblum +1

Multi-path speculative decoding accelerates lossless sampling from a target model by using a cheaper draft model to generate a draft tree of tokens, and then applies a verification…

cs.IT2026

Greedy Multi-Path Block Verification for Faster Decoding in Speculative Sampling

Rahul Thomas, Arka Pal

The goal of -step speculative decoding is to accelerate autoregressive decoding of a target model by using a cheaper draft model to generate a candidate path of tokens. Base…

cs.LG2025

Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Minimization

Rahul Krishna Thomas, Arka Pal

Speculative sampling reduces the latency of autoregressive decoding for target model LLMs without sacrificing inference quality, by using a cheap draft model to suggest a candidate…

cs.LG2025

Cascade: Token-Sharded Private LLM Inference

Rahul Thomas, Louai Zahran, Erica Choi +3

As LLMs continue to increase in parameter size, the computational resources required to run them are available to fewer parties. Therefore, third-party inference services -- where…

cs.CR2025

An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs

Rahul Thomas, Louai Zahran, Erica Choi +3

Recent advances in Large Language Models (LLMs) have led to the widespread adoption of third-party inference services, raising critical privacy concerns. Existing methods of perfor…