arXiv:2609.17241v1 Announce Type: new Abstract: While draft-model-free speculative decoding offers a promising path to efficient LLM inference, it is frequently constrained by stale draft candidates...
LoopAhead is a speculative decoding framework designed for looped Transformers, which repeatedly apply the same Transformer layers to improve parameter efficiency. It introduces a lightweight lookahead drafter (LAD) that predicts multiple future tokens using early-loop states, while deeper-loop feedback determines which draft branches to continue or pause, and the full-depth model finalizes token decisions. This approach achieves up to 7.82× faster decoding than traditional autoregressive methods while maintaining the target model’s output distribution.
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.
arXiv:2609.36590v1 Announce Type: cross Abstract: Self-speculative decoding accelerates large language model (LLM) inference by drafting tokens from the target model itself, but faces a sharp tradeof...
arXiv:2609.17184v1 Announce Type: new Abstract: Looped Transformers achieve strong performance with compact parameter sizes by repeatedly applying a shared stack of Transformer blocks across recurren...
The paper introduces TSS, a target-side sparsification framework that selectively skips layers in a target verifier during speculative decoding for domain-specific large language models. By exploring multi-layer skip configurations with an acceptance- and metric-aware breadth search, TSS reduces verification cost, increases draft acceptance, and can even improve downstream task performance without retraining. Experiments on Spec-Bench demonstrate consistent gains across domains and model scales, notably boosting translation throughput by 1.68× and improving BLEU scores significantly.
WaveFront Decoding (WFD) is a training‑free, self‑speculative decoding framework for looped language models that reduces decoding latency by batching draft and verification steps within the same recurrent‑block calls. By exploiting intermediate recurrence outputs as draft predictions and weight sharing to process token states at different depths together, WFD arranges mixed‑depth states into a diagonal wavefront, allowing shallow‑depth drafting while deeper‑depth verification proceeds concurrently. Experiments on six Spec‑Bench task categories show WFD achieving up to 4.81× speedup on Huginn‑3.5B compared to autoregressive decoding, outperforming traditional draft‑then‑verify approaches.
arXiv:2609.24698v1 Announce Type: new Abstract: Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which foll...
arXiv:2606. 12243v1 Announce Type: cross Abstract: Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel.
FlexEE is an early‑exiting framework designed for large language model inference that is constrained by computation and memory, particularly in offloading‑based deployments. It uses layer‑wise exit supervision, self‑speculative decoding over a Top‑K local vocabulary, and dynamic hidden‑state management to enable reliable intermediate‑layer predictions and memory‑aware execution. Experiments on Llama2‑7B and Llama3‑8B show that FlexEE achieves significant speedups—up to 1.27×/3.16× and 1.25×/2.83× respectively—while maintaining minimal accuracy loss.
Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically relies on auxiliary draft modules, incurring significant training and communication overhead.
The paper introduces DLoop, a looped speculative decoding technique that adaptively performs multiple drafting stages before verification, allowing a draft model to continue generating tokens while confident. By verifying all accumulated draft tokens together and training the draft model to handle its own hidden states for unverified tokens, DLoop reduces the number of target‑model forward passes needed. Experiments across several speculative decoding methods show wall‑clock speedups of 5–41 % without sacrificing lossless decoding.