Saved in:
Bibliographic Details
Main Authors: Abramovich, Talor, Ashkenazi, Maor, Putterman, Izzy, Chislett, Benjamin, Mitra, Tiyasa, Rouhani, Bita Darvish, Zilberstein, Ran, Geifman, Yonatan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.09557
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918529363607552
author Abramovich, Talor
Ashkenazi, Maor
Putterman, Izzy
Chislett, Benjamin
Mitra, Tiyasa
Rouhani, Bita Darvish
Zilberstein, Ran
Geifman, Yonatan
author_facet Abramovich, Talor
Ashkenazi, Maor
Putterman, Izzy
Chislett, Benjamin
Mitra, Tiyasa
Rouhani, Bita Darvish
Zilberstein, Ran
Geifman, Yonatan
contents Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and representative workloads are essential for accurately measuring its effectiveness. Existing benchmarks suffer from limited task diversity, inadequate support for throughput-oriented evaluation, and a reliance on high-level implementations that fail to reflect production environments. To address this, we introduce SPEED-Bench, a comprehensive suite designed to standardize SD evaluation across diverse semantic domains and realistic serving regimes. SPEED-Bench offers a carefully curated Qualitative data split, selected by prioritizing semantic diversity across the data samples. Additionally, it includes a Throughput data split, allowing speedup evaluation across a range of concurrencies, from latency-sensitive low-batch settings to throughput-oriented high-load scenarios. By integrating with production engines like vLLM and TensorRT-LLM, SPEED-Bench allows practitioners to analyze system behaviors often masked by other benchmarks. We highlight this by quantifying how synthetic inputs overestimate real-world throughput, identifying batch-size dependent optimal draft lengths and biases in low-diversity data, and analyzing the caveats of vocabulary pruning in state-of-the-art drafters. We release SPEED-Bench to establish a unified evaluation standard for practical comparisons of SD algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2604_09557
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
Abramovich, Talor
Ashkenazi, Maor
Putterman, Izzy
Chislett, Benjamin
Mitra, Tiyasa
Rouhani, Bita Darvish
Zilberstein, Ran
Geifman, Yonatan
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and representative workloads are essential for accurately measuring its effectiveness. Existing benchmarks suffer from limited task diversity, inadequate support for throughput-oriented evaluation, and a reliance on high-level implementations that fail to reflect production environments. To address this, we introduce SPEED-Bench, a comprehensive suite designed to standardize SD evaluation across diverse semantic domains and realistic serving regimes. SPEED-Bench offers a carefully curated Qualitative data split, selected by prioritizing semantic diversity across the data samples. Additionally, it includes a Throughput data split, allowing speedup evaluation across a range of concurrencies, from latency-sensitive low-batch settings to throughput-oriented high-load scenarios. By integrating with production engines like vLLM and TensorRT-LLM, SPEED-Bench allows practitioners to analyze system behaviors often masked by other benchmarks. We highlight this by quantifying how synthetic inputs overestimate real-world throughput, identifying batch-size dependent optimal draft lengths and biases in low-diversity data, and analyzing the caveats of vocabulary pruning in state-of-the-art drafters. We release SPEED-Bench to establish a unified evaluation standard for practical comparisons of SD algorithms.
title SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
url https://arxiv.org/abs/2604.09557