Cover Image

Accelerating Prefilling via Decoding-time Contribution Sparsity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Zhiyuan, Zhang, Yike, Zhang, Chengruidong, Jiang, Huiqiang, Yang, Yuqing, Qiu, Lili
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LeanK: Learnable K Cache Channel Pruning for Efficient Decoding
by: Zhang, Yike, et al.
Published: (2025)

MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
by: Li, Wenxuan, et al.
Published: (2025)

Position Engineering: Boosting Large Language Models through Positional Information Manipulation
by: He, Zhiyuan, et al.
Published: (2024)

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
by: Liu, Di, et al.
Published: (2024)

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
by: Jiang, Huiqiang, et al.
Published: (2024)

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
by: Jiang, Huiqiang, et al.
Published: (2023)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods
by: Li, Yucheng, et al.
Published: (2024)

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression
by: Li, Yucheng, et al.
Published: (2025)

UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
by: Fan, Qihang, et al.
Published: (2026)

MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
by: Li, Yucheng, et al.
Published: (2025)

PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference
by: Zhang, Hao, et al.
Published: (2025)

Mitigate Position Bias in Large Language Models via Scaling a Single Dimension
by: Yu, Yijiong, et al.
Published: (2024)

Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely
by: Zhao, Siyun, et al.
Published: (2024)

Chain-of-Model Learning for Language Model
by: Song, Kaitao, et al.
Published: (2025)

FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration
by: Jo, Dongwon, et al.
Published: (2025)

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs
by: Lu, Haiquan, et al.
Published: (2026)

SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
by: Zhang, Yiqi, et al.
Published: (2026)

CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs
by: Lv, Junlin, et al.
Published: (2024)

Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
by: Zhu, Yifan, et al.
Published: (2026)

Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing
by: Liu, Ziyang
Published: (2026)

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection
by: Song, Jiwon, et al.
Published: (2026)

Accelerating Prefilling for Long-Context LLMs via Sparse Pattern Sharing
by: Peng, Dan, et al.
Published: (2025)

AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache
by: Song, Dinghong, et al.
Published: (2025)

FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
by: Fan, Qihang, et al.
Published: (2026)

CLAA: Cross-Layer Attention Aggregation for Accelerating LLM Prefill
by: McDanel, Bradley, et al.
Published: (2026)

Region-Adaptive Sampling for Diffusion Transformers
by: Liu, Ziming, et al.
Published: (2025)

VL Norm: Rethink Loss Aggregation in RLVR
by: He, Zhiyuan, et al.
Published: (2025)

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
by: Pan, Zhuoshi, et al.
Published: (2024)

On Memory Construction and Retrieval for Personalized Conversational Agents
by: Pan, Zhuoshi, et al.
Published: (2025)

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
by: Tang, Zecheng, et al.
Published: (2026)

Acceleration Multiple Heads Decoding for LLM via Dynamic Tree Attention
by: Zhang, Zhendong
Published: (2025)

Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning
by: Li, Siwei, et al.
Published: (2024)

Sparsity-Accelerated Training for Large Language Models
by: Ma, Da, et al.
Published: (2024)

Exploring the Benefit of Activation Sparsity in Pre-training
by: Zhang, Zhengyan, et al.
Published: (2024)

SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding
by: Wang, Zhenglin, et al.
Published: (2024)

Cost-Aware Diffusion Draft Trees for Speculative Decoding
by: Zhang, Shuai, et al.
Published: (2026)

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
by: Ding, Yiran, et al.
Published: (2024)

BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
by: Song, Chenyang, et al.
Published: (2025)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
by: Liu, Jingyu, et al.
Published: (2025)

POP: Prefill-Only Pruning for Efficient Large Model Inference
by: He, Junhui, et al.
Published: (2026)