paper-with-me

홈 › Papers

VIA-SD: Verification via Intra-Model Routing for Speculative Decoding

2026-06-10 · Yuchen Xian, Yang He, Yunqiu Xu, Yi Yang arxiv

Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel. Existing draft-verify methods use binary decisions: accept or fully recompute. Yet we find that many rejected tokens can be verified correctly by a slim submodel derived from the full verifier via intra-model routing, instead of the full verifier. This motivates our slim-verifier to handle tokens requiring moderate verification resources, reducing expensive large-model calls. We propose Verification via Intra-Model Routing for Speculative Decoding (VIA-SD), a multi-tier framework using a routed slim-verifier. Draft tokens are processed hierarchically: direct acceptance for high-confidence cases, slim-verifier regeneration for medium-confidence cases, and full-model verification for uncertain cases. Across four representative tasks and multiple model families, VIA-SD reduces rejection rates by 0.10-0.22 and delivers 10-20% speedups over strong SD baselines, while achieving 2.5-3x acceleration over non-drafting decoding. Moreover, VIA-SD is compatible with existing SD frameworks without modifying their training procedures. Our results suggest multi-tier SD as a general paradigm for scalable and efficient LLM inference. Project page: https://zju-xyc.github.io/VIA-SD-Project-Page/

📄 PDF Abstract BibTeX arXiv:2606.12243

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding

2026-01-09 · Yuxuan Zhou, Fei Huang, Heng Li, Fengyi Wu 외 arxiv

Verification is a key bottleneck in improving inference speed while maintaining distribution fidelity in Speculative Decoding. Recent work has shown that sequence-level verification leads to a higher number of accepted t…

S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices

2026-08-15 · Haochen Huang, Shengxuan Qiu, Meng Li arxiv

Deploying large language models (LLMs) for inference on edge devices is challenging due to severe memory and bandwidth constraints. While speculative decoding and Mixture-of-Experts (MoE) have been proposed to improve in…

TAPS: Task Aware Proposal Distributions for Speculative Sampling

2026-03-27 · Mohamad Zbib, Mohamad Bazzi, Ammar Mohanna, Hasan Abed Al Kader Hammoud 외 arxiv

Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In practice, however, draft models are usually t…

Speculative Speculative Decoding

2026-03-03 · Tanishq Kumar, Tri Dao, Avner May arxiv

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, …

SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models

2025-05-12 · Hang Wu, Jianian Zhu, Yinghui Li, Haojie Wang 외

Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but les…

Scheduling