Pereg, Oren

2 publications

ICML 2025 Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Gaurav Jain, Oren Pereg, Moshe Wasserblat, David Harel

ICLR 2025 Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Oren Pereg, Moshe Wasserblat, Tomer Galanti, Michal Gordon-Kiwkowitz, David Harel