arXiv:2608. 08721v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by drafting multiple tokens for parallel verification, with efficiency critically determined by the speculative length selected at each decoding round.
arXiv:2606. 04446v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive large language model inference by drafting multiple tokens and verifying them in a single target-model forward pass.
arXiv:2607. 08690v1 Announce Type: cross Abstract: Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM.
Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard speculative decoding is lossless: its rejection and resampling steps exactly preserve the LLM's sampling distribution.
arXiv:2607. 19223v1 Announce Type: new Abstract: Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference.
Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation. Speculative decoding addresses this bottleneck by employing a lightweight draft model to propose multiple future tokens that are subsequently verified in parallel by a larger target model.
arXiv:2606. 02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding.
The efficiency of Large Language Model (LLM) serving is fundamentally limited by the sequential nature of autoregressive decoding. Speculative Decoding (SD) mitigates this by using a lightweight draft...
arXiv:2607. 12696v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) models have become an important approach for scaling Large Language Models (LLMs), but their inference efficiency depends strongly on expert activation patterns.
arXiv:2606. 11552v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation.
ResiSpec is a framework that improves speculative decoding for large language models by reshaping the residual distribution during verification. It addresses the problem of residual drift, where rejected candidates cause the target distribution to diverge from the draft model’s predictions, rendering later candidates ineffective. By aligning the verification process with the draft model’s high‑confidence regions, ResiSpec prevents candidate obsolescence and achieves up to 1.92× speedup over existing multi‑candidate methods.
The paper introduces a trajectory-level speculative decoding framework for diffusion-based language models (dLLMs), addressing the limitation of existing strategies that revert to single-token generation when confidence is low. By constructing draft denoising trajectories through confidence-stratified tree exploration and verifying them with blockwise parallel evaluation and bidirectional attention masking, the method also incorporates inter-block speculation to exploit the models’ bidirectional structure. Experiments show a 30–40% reduction in denoising iterations, a token-per-step increase from 2.6 to 4.3, and a 7–14× speedup over vanilla dLLMs while maintaining accuracy within 1% on reasoning and code benchmarks.
Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference. Recent work such as DFlash further boosts drafting efficiency by leveraging diffusion drafters, whose parallel denoising mechanism enables draft generation in a single forward pass.