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

• URL: http://arxiv.org/abs/2505.07680v1
• Date: Mon, 12 May 2025 15:46:28 GMT
• Title: SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models
• Authors: Hang Wu, Jianian Zhu, Yinghui Li, Haojie Wang, Biao Hou, Jidong Zhai,
• Abstract summary: Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost.<n>Existing serving strategies often employ fixed model scales or static two-stage speculative decoding.<n>This paper introduces systemname, a novel framework that reimagines LLM inference as an adaptive routing problem.
• Score: 21.933379266533098
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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 less powerful. Existing serving strategies often employ fixed model scales or static two-stage speculative decoding, failing to dynamically adapt to the varying complexities of user requests or fluctuations in system performance. This paper introduces \systemname{}, a novel framework that reimagines LLM inference as an adaptive routing problem solved through multi-level speculative decoding. \systemname{} dynamically constructs and optimizes inference "paths" (chains of models) based on real-time feedback, addressing the limitations of static approaches. Our contributions are threefold: (1) An \textbf{adaptive model chain scheduling} mechanism that leverages performance profiling (execution times) and predictive similarity metrics (derived from token distribution divergence) to continuously select the optimal sequence of draft and verifier models, minimizing predicted latency per generated token. (2) A \textbf{multi-level collaborative verification} framework where intermediate models within the selected chain can validate speculative tokens, reducing the verification burden on the final, most powerful target model. (3) A \textbf{synchronized state management} system providing efficient, consistent KV cache handling across heterogeneous models in the chain, including precise, low-overhead rollbacks tailored for asynchronous batch processing inherent in multi-level speculation. Preliminary experiments demonstrate the validity of our method.

Related papers

• FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation [50.438552588818]
  We propose textbfFindRec (textbfFlexible unified textbfinformation textbfdisentanglement for multi-modal sequential textbfRecommendation)<n>A Stein kernel-based Integrated Information Coordination Module (IICM) theoretically guarantees distribution consistency between multimodal features and ID streams.<n>A cross-modal expert routing mechanism that adaptively filters and combines multimodal features based on their contextual relevance.
  arXiv  Detail & Related papers  (2025-07-07T04:09:45Z)
• Transferable Sequential Recommendation with Vanilla Cross-Entropy Loss [2.0048375809706274]
  Sequential Recommendation (SR) systems model user preferences by analyzing interaction histories.<n>Current methods incur substantial fine-tuning costs when adapting to new domains.<n>We propose MMM4Rec, a novel multi-modal SR framework that incorporates a dedicated algebraic constraint mechanism for efficient transfer learning.
  arXiv  Detail & Related papers  (2025-06-03T14:18:19Z)
• Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models [50.19188692497892]
  Traditional alignment methods often require retraining large pretrained models.<n>We propose a novel textitResidual Alignment Model (textitRAM) that formalizes the alignment process as a type of importance sampling.<n>We develop a resampling algorithm with iterative token-level decoding to address the common first-token latency issue in comparable methods.
  arXiv  Detail & Related papers  (2025-05-26T08:53:02Z)
• Activation-Guided Consensus Merging for Large Language Models [25.68958388022476]
  We present textbfActivation-Guided textbfConsensus textbfMerging (textbfACM), a plug-and-play merging framework that determines layer-specific merging coefficients.<n>Experiments on Long-to-Short (L2S) and general merging tasks demonstrate that ACM consistently outperforms all baseline methods.
  arXiv  Detail & Related papers  (2025-05-20T07:04:01Z)
• Communication-Efficient Wireless Federated Fine-Tuning for Large-Scale AI Models [13.742950928229078]
  Low-Rank Adaptation (LoRA) addresses these issues by training compact, low-rank matrices instead of fully fine-tuning large models.<n>This paper introduces a wireless federated LoRA fine-tuning framework that optimize both learning performance and communication efficiency.
  arXiv  Detail & Related papers  (2025-05-01T06:15:38Z)
• DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models [50.32663816994459]
  Diffusion-styled Preference Optimization (model) provides an efficient and policy-agnostic solution for aligning LLMs with humans.<n>modelavoids the time latency associated with token-level generation.<n>Experiments on AlpacaEval 2, MT-bench, and HH-RLHF demonstrate that modelachieves superior alignment performance across various settings.
  arXiv  Detail & Related papers  (2025-03-06T09:21:54Z)
• Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging [75.93960998357812]
  Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their capabilities across different tasks and domains.<n>Current model merging techniques focus on merging all available models simultaneously, with weight matrices-based methods being the predominant approaches.<n>We propose a training-free projection-based continual merging method that processes models sequentially.
  arXiv  Detail & Related papers  (2025-01-16T13:17:24Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Adaptive Draft-Verification for Efficient Large Language Model Decoding [24.347886232342862]
  Large language model (LLM) decoding involves generating a sequence of tokens based on a given context. The typical autoregressive decoding method requires a separate forward pass through the model for each token generated. We introduce ADED, which accelerates LLM decoding without requiring fine-tuning.
  arXiv  Detail & Related papers  (2024-06-27T22:20:39Z)
• Flover: A Temporal Fusion Framework for Efficient Autoregressive Model Parallel Inference [3.005912820808423]
  Inference on autoregressive models harnesses a temporal dependency, where the current token's probability distribution is conditioned on preceding tokens. We propose Flover -- a temporal fusion framework for efficiently inferring multiple requests in parallel. By orchestrating the token-level parallelism, Flover exhibits hardware optimal efficiency and significantly spares the system resources.
  arXiv  Detail & Related papers  (2023-05-22T20:58:09Z)
• Bayesian Prompt Learning for Image-Language Model Generalization [64.50204877434878]
  We use the regularization ability of Bayesian methods to frame prompt learning as a variational inference problem. Our approach regularizes the prompt space, reduces overfitting to the seen prompts and improves the prompt generalization on unseen prompts. We demonstrate empirically on 15 benchmarks that Bayesian prompt learning provides an appropriate coverage of the prompt space.
  arXiv  Detail & Related papers  (2022-10-05T17:05:56Z)
• Slimmable Domain Adaptation [112.19652651687402]
  We introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank. Our framework surpasses other competing approaches by a very large margin on multiple benchmarks.
  arXiv  Detail & Related papers  (2022-06-14T06:28:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.