跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.22296 · v1

SpecSearch: Towards Hardware-Aware Efficient Speculative Decoding

首次提交 2026-11-17 14:53
版本更新 2026-11-17 14:53
雷达观测 2026-11-18 19:43
arXiv ↗PDF ↗

摘要

Speculative decoding (SD) accelerates large language model (LLM) inference, but its optimal configuration depends jointly on workload characteristics, GPU hardware, and available memory. For example, on the RTX~5090, the state-of-the-art speculative drafter DFlash achieves 3.50×3.50\times the throughput of autoregressive (AR) decoding at low concurrency, but only 0.76×0.76\times at high concurrency with short outputs. We present SpecSearch, a hardware-aware search engine that jointly optimizes decoding strategy, draft length, and precision across workload--GPU pairs. Its analytical cost model captures memory and compute constraints to identify feasible configurations and narrow the search space for throughput optimization. Guided by this model, calibration measurements are collected from multiple GPUs. Using the measurements, a Jev-based predictor learns to select high-throughput decoding configurations on held-out GPUs without requiring deployment-GPU calibration. The predictor is parameter-efficiently trained on calibration data, while adapting a frozen Qwen3-4B using LoRA adapters and a linear correction layer. Across NVIDIA RTX~5090, H100, L40 and AMD MI300X GPUs, SpecSearch with full calibration achieves an average of 2.01×2.01\times the throughput of AR and 1.36×1.36\times the throughput of SD, both served by vLLM. The proposed Jev-based predictor closely matches this search performance with 1.30×1.30\times throughput improvement over SD with vLLM, while eliminating the need for held-out GPU calibration. Additionally, it retains 97.36%97.36\% of the throughput achieved by SpecSearch that utilizes full calibration.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-17 14:53 · 最新观测版本

SpecSearch: Towards Hardware-Aware Efficient Speculative Decoding

Speculative decoding (SD) accelerates large language model (LLM) inference, but its optimal configuration depends jointly on workload characteristics, GPU hardware, and available memory. For example, on the RTX~5090, the state-of-the-art speculative drafter DFlash achieves 3.50×3.50\times the throughput of autoregressive (AR) decoding at low concurrency, but only 0.76×0.76\times at high concurrency with short outputs. We present SpecSearch, a hardware-aware search engine that jointly optimizes decoding strategy, draft length, and precision across workload--GPU pairs. Its analytical cost model captures memory and compute constraints to identify feasible configurations and narrow the search space for throughput optimization. Guided by this model, calibration measurements are collected from multiple GPUs. Using the measurements, a Jev-based predictor learns to select high-throughput decoding configurations on held-out GPUs without requiring deployment-GPU calibration. The predictor is parameter-efficiently trained on calibration data, while adapting a frozen Qwen3-4B using LoRA adapters and a linear correction layer. Across NVIDIA RTX~5090, H100, L40 and AMD MI300X GPUs, SpecSearch with full calibration achieves an average of 2.01×2.01\times the throughput of AR and 1.36×1.36\times the throughput of SD, both served by vLLM. The proposed Jev-based predictor closely matches this search performance with 1.30×1.30\times throughput improvement over SD with vLLM, while eliminating the need for held-out GPU calibration. Additionally, it retains 97.36%97.36\% of the throughput achieved by SpecSearch that utilizes full calibration.

查看此版本解读 →查看此版本原文 ↗