Cover Image

Pipeline Parallelism is All You Need for Optimized Early-Exit Based Self-Speculative Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Ruanjun, Liu, Ziheng, Shi, Yuanming, Shao, Jiawei, Zhang, Chi, Li, Xuelong
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
by: Elhoushi, Mostafa, et al.
Published: (2024)

One Jump Is All You Need: Short-Cutting Transformers for Early Exit Prediction with One Jump to Fit All Exit Levels
by: Seshadri, Amrit Diggavi
Published: (2025)

The Diminishing Returns of Early-Exit Decoding in Modern LLMs
by: Wei, Rui, et al.
Published: (2026)

CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
by: Ning, Zhiyuan, et al.
Published: (2025)

PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
by: An, Zihao, et al.
Published: (2026)

Not All Documents Are What You Need for Extracting Instruction Tuning Data
by: Zhang, Chi, et al.
Published: (2025)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
by: Yang, Rubing, et al.
Published: (2025)

Training on the Benchmark Is Not All You Need
by: Ni, Shiwen, et al.
Published: (2024)

ScRPO: From Errors to Insights
by: Li, Lianrui, et al.
Published: (2025)

Tensor Product Attention Is All You Need
by: Zhang, Yifan, et al.
Published: (2025)

Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compression
by: Yuan, Cheng, et al.
Published: (2025)

Contrast Is All You Need
by: Kilic, Burak, et al.
Published: (2023)

Speculative Decoding for Multi-Sample Inference
by: Li, Yiwei, et al.
Published: (2025)

Self-Verification is All You Need To Pass The Japanese Bar Examination
by: Shin, Andrew
Published: (2026)

More Agents Is All You Need
by: Li, Junyou, et al.
Published: (2024)

Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding
by: Hu, Shijing, et al.
Published: (2025)

Traversal Verification for Speculative Tree Decoding
by: Weng, Yepeng, et al.
Published: (2025)

Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
by: Li, Jinze, et al.
Published: (2025)

Dynamic Early Exit in Reasoning Models
by: Yang, Chenxu, et al.
Published: (2025)

Is Depth All You Need? An Exploration of Iterative Reasoning in LLMs
by: Wu, Zongqian, et al.
Published: (2025)

Rho-1: Not All Tokens Are What You Need
by: Lin, Zhenghao, et al.
Published: (2024)

Speculative Decoding: Performance or Illusion?
by: Liu, Xiaoxuan, et al.
Published: (2025)

Agents Are All You Need for LLM Unlearning
by: Sanyal, Debdeep, et al.
Published: (2025)

Batch Speculative Decoding Done Right
by: Zhang, Ranran Haoran, et al.
Published: (2025)

Attention Smoothing Is All You Need For Unlearning
by: Zade, Saleh Zare, et al.
Published: (2026)

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
by: Yoon, Kanghoon, et al.
Published: (2025)

Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection
by: Gao, Weizhi, et al.
Published: (2025)

Online Speculative Decoding
by: Liu, Xiaoxuan, et al.
Published: (2023)

Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization
by: Dong, Zhijin
Published: (2025)

The Disparate Impacts of Speculative Decoding
by: Sandler, Jameson, et al.
Published: (2025)

Constrained Decoding with Speculative Lookaheads
by: Nakshatri, Nishanth, et al.
Published: (2024)

Scaling Laws for Speculative Decoding
by: Yan, Siyuan, et al.
Published: (2025)

Cross-Attention Speculative Decoding
by: Zhong, Wei, et al.
Published: (2025)

Mamba Drafters for Speculative Decoding
by: Choi, Daewon, et al.
Published: (2025)

RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding
by: Zhang, Zihong, et al.
Published: (2026)

Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
by: Jin, Tao, et al.
Published: (2026)

Self-Speculative Biased Decoding for Faster Re-Translation
by: Zeng, Linxiao, et al.
Published: (2025)

GRIFFIN: Effective Token Alignment for Faster Speculative Decoding
by: Hu, Shijing, et al.
Published: (2025)

Dynamic Depth Decoding: Faster Speculative Decoding for LLMs
by: Brown, Oscar, et al.
Published: (2024)

Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits
by: Venkatesha, Yeshwanth, et al.
Published: (2025)