7 papers
Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
Nadav Timor, Jonathan Mamou, Daniel Korat +5
Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generat…
Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference
Nadav Timor, Jonathan Mamou, Daniel Korat +6
This paper introduces distributed speculative inference (DSI), a novel inference algorithm that is provably faster than speculative inference (SI) [leviathan2023, chen2023, miao202…
HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly
Howard Yen, Tianyu Gao, Minmin Hou +5
Many benchmarks exist for evaluating long-context language models (LCLMs), yet developers often rely on synthetic tasks such as needle-in-a-haystack (NIAH) or an arbitrary subset o…
SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models
Daniel Fleischer, Moshe Berchansky, Gad Markovits +1
In the rapidly evolving field of Natural Language Processing, Large Language Models (LLMs) are tasked with increasingly complex reasoning challenges. Traditional methods like chain…
CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity
Moshe Berchansky, Daniel Fleischer, Moshe Wasserblat +1
State-of-the-art performance in QA tasks is currently achieved by systems employing Large Language Models (LLMs), however these models tend to hallucinate information in their resp…
Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models
Jonathan Mamou, Oren Pereg, Daniel Korat +4
Speculative decoding is commonly used for reducing the inference latency of large language models. Its effectiveness depends highly on the speculation lookahead (SL)-the number of…