Cover Image

UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fan, Qihang, Huang, Huaibo, Wu, Zhiying, Wang, Bingning, He, Ran
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

Block-Attention for Efficient Prefilling
by: Ma, Dongyang, et al.
Published: (2024)

Accelerating Prefilling via Decoding-time Contribution Sparsity
by: He, Zhiyuan, et al.
Published: (2025)

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

Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models
by: Upasani, Shubhangi, et al.
Published: (2026)

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

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

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

FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
by: Lai, Xunhao, et al.
Published: (2025)

FAST-Prefill: FPGA Accelerated Sparse Attention for Long Context LLM Prefill
by: Jayanth, Rakshith, et al.
Published: (2026)

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

LLM Router: Rethinking Routing with Prefill Activations
by: Varshney, Tanay, et al.
Published: (2026)

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

Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization
by: Dotsinski, Asen, et al.
Published: (2026)

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

PreFT: Prefill-only finetuning for efficient inference
by: Lanpouthakoun, Andrew, et al.
Published: (2026)

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

Breaking the Low-Rank Dilemma of Linear Attention
by: Fan, Qihang, et al.
Published: (2024)

Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling
by: Cappelletti, Silvia, et al.
Published: (2025)

SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation
by: Qiao, Aurick, et al.
Published: (2024)

IntroLM: Introspective Language Models via Prefilling-Time Self-Evaluation
by: Kasnavieh, Hossein Hosseini, et al.
Published: (2026)

FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving
by: Hsieh, Chia-chi, et al.
Published: (2026)

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
by: Struppek, Lukas, et al.
Published: (2026)

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

Prefill-Guided Thinking for zero-shot detection of AI-generated images
by: Kachwala, Zoher, et al.
Published: (2025)

PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications
by: Du, Kuntai, et al.
Published: (2025)

Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models
by: Zhao, Siyan, et al.
Published: (2024)

Random Wins All: Rethinking Grouping Strategies for Vision Tokens
by: Fan, Qihang, et al.
Published: (2026)

Rectifying Magnitude Neglect in Linear Attention
by: Fan, Qihang, et al.
Published: (2025)

Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens
by: Fan, Qihang, et al.
Published: (2024)

Lightweight Vision Transformer with Bidirectional Interaction
by: Fan, Qihang, et al.
Published: (2023)

Let's Put Ourselves in Sally's Shoes: Shoes-of-Others Prefilling Improves Theory of Mind in Large Language Models
by: Shinoda, Kazutoshi, et al.
Published: (2025)

Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention
by: Ai, Yuang, et al.
Published: (2025)

PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
by: Woo, Sunghyeon, et al.
Published: (2026)

LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation
by: Dong, Zican, et al.
Published: (2025)

APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
by: Huang, Yuxiang, et al.
Published: (2025)

ContiguousKV: Accelerating LLM Prefill with Granularity-Aligned KV Cache Management
by: Zou, Jing, et al.
Published: (2026)

SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning
by: Long, Lingkun, et al.
Published: (2025)