SOURCE-LINKED INTELLIGENCE

A rigor-matched audit of periodic-step layer skipping for efficient llm inference: conflayers versus swift, with a supplemental analysis of trained routing alternatives

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Layer-skipping methods for efficient LLM inference decide, at some granularity, which transformer layers to execute for a given input. We present a rigor-matched, three-seed audit of two periodic-step, search-based methods that make this decision online at inference time and re-evaluate it every few generation steps: a confidence-gated early-exit baseline (ConfLayers) and genuine self-speculative decoding (SWIFT, Xia et al. 2024), together with vanilla autoregressive decoding, across Qwen2.5-0.5B and Qwen2.5-1.5B (Yang et al. 2024) on GSM8K (Cobbe et al. 2021) and CNN/DailyMail (Nallapati et a

Read original source ↗ Open in workspace

recordType

paper

region

Global