The paper introduces Decoupled Contrastive Decoding (DCD), a method that separates drafting from verification in contrastive decoding. DCD uses an expert‑aligned lightweight proposer for drafting and applies contrastive correction only during verification, preserving the vanilla contrastive decoding distribution. Experiments on 8B models show that DCD achieves 1.65–1.95× speedups in greedy decoding and reduces MMLU proposal‑path latency by 5–12× compared to amateur‑coupled approaches.
Contrastive Decoding (CD) improves generation quality, but its amateur-model pass makes decoding expensive. Accelerating CD with speculative decoding raises a proposal-alignment question: should the contrastive signal shape the drafter, or should it remain only in verification?
arXiv:2610.00623v1 Announce Type: new Abstract: Speculative decoding has achieved substantial lossless speedups for LLMs, but remains less effective for large vision-language models (LVLMs), where li...
The paper introduces AdaptiveSpec, a training‑free speculative decoding method that simultaneously adapts the per‑step verification rule and the draft‑tree shape using signals generated during decoding. It replaces the fixed token‑match rule with a margin‑based threshold and adjusts tree depth, width, and node count based on draft confidence and recent acceptance history, allowing the total draft count to vary. Experiments on SGLang show up to 56% throughput gains over EAGLE‑3 while maintaining 93% of lossless task accuracy on GSM8K, MATH‑500, and HumanEval across three models.
arXiv:2606. 26744v1 Announce Type: new Abstract: We present HyperDFlash, a block-parallel speculative decoding framework tailored to the novel multi-hyper-connection (MHC) architecture proposed by DeepSeek-V4.
arXiv:2606. 26744v2 Announce Type: replace Abstract: We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC).
The paper introduces DPara, a parallel speculative decoding framework that builds on DSpark-style parallel drafters. DPara eliminates the need for probabilistic guesses by precomputing draft representations for every acceptance boundary and using a lightweight autoregressive head to combine verification outcomes with these representations, enabling full parallelization of the backbone forward pass. Experiments on Qwen3-8B and Qwen3-14B across multiple benchmarks demonstrate average speedups of 3.21× and 3.52× over autoregressive decoding, outperforming existing serial and parallel speculative decoding methods.
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
arXiv:2611.05724v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference with a small drafter, whose per-guess acceptance rate determines the achievable speedup...
arXiv:2610.07822v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by using a lightweight draft model to propose multiple tokens that are verified by a target...
arXiv:2607. 27269v1 Announce Type: new Abstract: Multi-head latent attention (MLA) is increasingly important for long-context LLM inference because compact latent states replace the growing key-value (KV) cache and reduce decoding memory traffic.
The paper introduces APEX, a learned controller that improves speculative decoding for large language models by dynamically selecting the best speculation strategy and adjusting draft depth during generation. APEX uses request‑level routing among EAGLE‑3, n‑gram, and draft‑model speculation, and block‑level depth adaptation based on causal decoding signals and verifier feedback. Integrated into vLLM and tested with Qwen3‑8B, APEX achieves up to 5.24× speedup over autoregressive decoding while reducing wasted tokens by 41% compared to fixed‑depth n‑gram speculation.
arXiv:2610.27379v1 Announce Type: cross Abstract: Block-diffusion speculative decoding accelerates large language model inference by drafting multiple tokens in parallel. However, one-step drafting i...