collaborators

5 papers

cs.CL2026

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing

Raghavv Goel, Mukul Gagrani, Mingu Lee +1

Large Language Models (LLMs) possess latent multi-token prediction (MTP) abilities despite being trained only for next-token generation. We introduce ESP (Embedding-Space Probing),…

cs.CL2026

ConFu: Contemplate the Future for Better Speculative Sampling

Zongyue Qin, Raghavv Goel, Mukul Gagrani +3

Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models to propose candidate tokens that ar…

cs.LG2026

Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity

Aayush Gautam, Mukul Gagrani, Junyoung Park +3

The prefill stage of large language model (LLM) inference is a key computational bottleneck for long-context workloads. At short-to-moderate context lengths (1K--16K tokens), Feed-…

cs.LG2025

CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction

Raghavv Goel, Junyoung Park, Mukul Gagrani +5

While long context support of large language models has extended their abilities, it also incurs challenges in memory and compute which becomes crucial bottlenecks in resource-rest…

cs.CL2025

VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs

Raghavv Goel, Sudhanshu Agrawal, Mukul Gagrani +9

In this paper, we introduce a simple training-free technique to improve the performance of drafter-based speculative decoding (SpD) methods that incorporates language modeling head…