Pith. sign in

REVIEW 6 cited by

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.06916 v2 pith:NM3GVWSF submitted 2024-10-09 cs.CL

classification cs.CL
keywords swiftinferenceacrossdecodingdraftllmsmodelsadditional
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multiple tokens efficiently and then using the target LLM to verify them in parallel. While this technique has achieved notable speedups, most existing approaches necessitate either additional parameters or extensive training to construct effective draft models, thereby restricting their applicability across different LLMs and tasks. To address this limitation, we explore a novel plug-and-play SD solution with layer-skipping, which skips intermediate layers of the target LLM as the compact draft model. Our analysis reveals that LLMs exhibit great potential for self-acceleration through layer sparsity and the task-specific nature of this sparsity. Building on these insights, we introduce SWIFT, an on-the-fly self-speculative decoding algorithm that adaptively selects intermediate layers of LLMs to skip during inference. SWIFT does not require auxiliary models or additional training, making it a plug-and-play solution for accelerating LLM inference across diverse input data streams. Our extensive experiments across a wide range of models and downstream tasks demonstrate that SWIFT can achieve over a 1.3x-1.6x speedup while preserving the original distribution of the generated text. We release our code in https://github.com/hemingkx/SWIFT.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Dynamic Execution Commitment of Vision-Language-Action Models

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    A3 reframes dynamic action chunk commitment in VLA models as self-speculative prefix verification, accepting the longest continuous sequence of actions that satisfies consensus-ordered conditional invariance and prefi...

  2. SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

    cs.CV 2026-03 conditional novelty 7.0 of 10

    A small tool-free MLLM plus answer-separability gating bypasses agentic tool loops for many queries, yielding 1.1–3.35× speedup with preserved or higher accuracy.

  3. KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem

    cs.LG 2026-02 conditional novelty 6.0 of 10

    By modeling layer skipping as a knapsack problem with context-dependent attention/MLP latencies, KnapSpec adaptively selects draft sub-networks that speed up self-speculative decoding by up to 1.47×.

  4. HiSpec: Hierarchical Speculative Decoding for LLMs

    cs.CL 2025-10 conditional novelty 6.0 of 10

    HiSpec uses early-exit layers to verify draft tokens midway through the model, reporting 1.28×-2.01× faster decoding over baseline speculative decoding, but the accuracy claim is not empirically tested.

  5. CLaSp: In-Context Layer Skip for Self-Speculative Decoding

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A training-free, context-adaptive layer-skipping method for self-speculative decoding that reports roughly 1.1x to 1.8x speedups on LLaMA models while preserving output distribution.

  6. MixReasoning: Switching Modes to Think

    cs.AI 2025-10 conditional novelty 5.0 of 10

    A reasoning model can cut token usage by roughly a third to a half without losing accuracy if it switches to brief output on low-uncertainty steps and expands only at high-uncertainty forks.

Pith tools