Imagen de Portada

An experimental study of KV cache reuse strategies in chunk-level caching systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cestola, Samuel, Xia, Tianxiang, Weiyan, Zheng, Pengfei, Zheng, Didona, Diego
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Machine Learning I.2.7
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache
por: Wang, Xinhai, et al.
Publicado: (2026)

KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
por: Nadali, Alireza, et al.
Publicado: (2026)

Constraint-Driven Small Language Models Based on Agent and OpenAlex Knowledge Graph: Mining Conceptual Pathways and Discovering Innovation Points in Academic Papers
por: Xia, Ziye, et al.
Publicado: (2025)

Evaluating the Efficacy of Hybrid Deep Learning Models in Distinguishing AI-Generated Text
por: Oketunji, Abiodun Finbarrs
Publicado: (2023)

Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
por: Zhang, Zhaowei, et al.
Publicado: (2025)

Enhancing Automated Essay Scoring with Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training
por: Choi, Hongseok, et al.
Publicado: (2026)

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
por: Chauhan, Anay, et al.
Publicado: (2026)

Transactional Attention: Semantic Sponsorship for KV-Cache Retention
por: Basu, Abhinaba
Publicado: (2026)

Large Language Model (LLM) Bias Index -- LLMBI
por: Oketunji, Abiodun Finbarrs, et al.
Publicado: (2023)

Engineering A Large Language Model From Scratch
por: Oketunji, Abiodun Finbarrs
Publicado: (2024)

Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction
por: Garcia, Gabriel
Publicado: (2026)

Dual-Phase Federated Deep Unlearning via Weight-Aware Rollback and Reconstruction
por: Zhou, Changjun, et al.
Publicado: (2025)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
por: Fadli, Samih
Publicado: (2025)

Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph
por: Wang, Fali, et al.
Publicado: (2025)

Reasoning Over the Glyphs: Evaluation of LLM's Decipherment of Rare Scripts
por: Shih, Yu-Fei, et al.
Publicado: (2025)

MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problems
por: Ye, Xinwu, et al.
Publicado: (2025)

Influence-driven Curriculum Learning for Pre-training on Limited Data
por: Schoenegger, Loris, et al.
Publicado: (2025)

Towards Latent Diffusion Suitable For Text
por: Midavaine, Nesta, et al.
Publicado: (2026)

SpectralLoRA: Is Low-Frequency Structure Sufficient for LoRA Adaptation? A Spectral Analysis of Weight Updates
por: Singh, Rajveer
Publicado: (2026)

BLP-2023 Task 2: Sentiment Analysis
por: Hasan, Md. Arid, et al.
Publicado: (2023)

FIM-LoRA: Task-Informative Rank Allocation for LoRA via Calibration-Time Gradient-Variance Estimation
por: Sathyavageeswaran, Ramakrishnan
Publicado: (2026)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
por: Hanna, Michael, et al.
Publicado: (2024)

Integrating Expert Labels into LLM-based Emission Goal Detection: Example Selection vs Automatic Prompt Design
por: Wrzalik, Marco, et al.
Publicado: (2024)

Where Should LoRA Go? Component-Type Placement in Hybrid Language Models
por: Borobia, Hector, et al.
Publicado: (2026)

Interpreto: An Explainability Library for Transformers
por: Poché, Antonin, et al.
Publicado: (2025)

RightNow-Arabic-0.5B-Turbo: An Open Sub-1B Arabic Language Model via Vocabulary Injection and Edge-First Deployment
por: Jaber, Jaber, et al.
Publicado: (2026)

Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity
por: Zhao, Hangyue, et al.
Publicado: (2026)

Efficacy of ByT5 in Multilingual Translation of Biblical Texts for Underrepresented Languages
por: Aars, Corinne, et al.
Publicado: (2024)

GenAI Content Detection Task 3: Cross-Domain Machine-Generated Text Detection Challenge
por: Dugan, Liam, et al.
Publicado: (2025)

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training
por: Tian, Changxin, et al.
Publicado: (2025)

PowLU: An Activation Function for Stable Pre-Training of LLMs
por: Jiang, Peijie, et al.
Publicado: (2026)

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time
por: Zhao, Mingkuan, et al.
Publicado: (2026)

Reconstructing Syllable Sequences in Abugida Scripts with Incomplete Inputs
por: Thu, Ye Kyaw, et al.
Publicado: (2025)

Human-interpretable clustering of short-text using large language models
por: Miller, Justin K., et al.
Publicado: (2024)

Scaling Laws for Forgetting When Fine-Tuning Large Language Models
por: Kalajdzievski, Damjan
Publicado: (2024)

Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts
por: Chourasia, Shivam, et al.
Publicado: (2026)

Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction
por: Hosseini, Peyman, et al.
Publicado: (2023)

A Framework for Fine-Tuning LLMs using Heterogeneous Feedback
por: Aponte, Ryan, et al.
Publicado: (2024)

Ambiguity in LLMs is a concept missing problem
por: Hu, Zhibo, et al.
Publicado: (2025)

Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment
por: Zhang, Yizhuo, et al.
Publicado: (2025)