← 研踪 PaperTrailarXiv: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
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 the throughput of autoregressive (AR) decoding at low concurrency, but only 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 the throughput of AR and the throughput of SD, both served by vLLM. The proposed Jev-based predictor closely matches this search performance with throughput improvement over SD with vLLM, while eliminating the need for held-out GPU calibration. Additionally, it retains of the throughput achieved by SpecSearch that utilizes full calibration.
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 the throughput of autoregressive (AR) decoding at low concurrency, but only 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 the throughput of AR and the throughput of SD, both served by vLLM. The proposed Jev-based predictor closely matches this search performance with throughput improvement over SD with vLLM, while eliminating the need for held-out GPU calibration. Additionally, it retains of the throughput achieved by SpecSearch that utilizes full calibration.
查看此版本解读 →查看此版本原文 ↗