TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering
Fuente:
arXiv
Saved in:
| Main Authors: | Joshi, Vinay, Brahma, Pratik Prabhanjan, Liu, Zicheng, Barsoum, Emad |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection
by: Ray, Pretam, et al.
Published: (2026)
by: Ray, Pretam, et al.
Published: (2026)
SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers
by: Manem, Chaitanya, et al.
Published: (2025)
by: Manem, Chaitanya, et al.
Published: (2025)
Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks
by: Wang, Jianghui, et al.
Published: (2025)
by: Wang, Jianghui, et al.
Published: (2025)
DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
by: Singh, Aditya Kumar, et al.
Published: (2026)
by: Singh, Aditya Kumar, et al.
Published: (2026)
X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression
by: Li, Guihong, et al.
Published: (2025)
by: Li, Guihong, et al.
Published: (2025)
Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion
by: Singh, Shivam, et al.
Published: (2026)
by: Singh, Shivam, et al.
Published: (2026)
Instella: Fully Open Language Models with Stellar Performance
by: Liu, Jiang, et al.
Published: (2025)
by: Liu, Jiang, et al.
Published: (2025)
DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
by: Zhou, Xiabin, et al.
Published: (2024)
by: Zhou, Xiabin, et al.
Published: (2024)
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
by: Wu, Chengyue, et al.
Published: (2025)
by: Wu, Chengyue, et al.
Published: (2025)
FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration
by: Jo, Dongwon, et al.
Published: (2025)
by: Jo, Dongwon, et al.
Published: (2025)
PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference
by: Patel, Ishan, et al.
Published: (2026)
by: Patel, Ishan, et al.
Published: (2026)
SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
by: Liao, Huanxuan, et al.
Published: (2025)
by: Liao, Huanxuan, et al.
Published: (2025)
SABlock: Semantic-Aware KV Cache Eviction with Adaptive Compression Block Size
by: Chen, Jinhan, et al.
Published: (2025)
by: Chen, Jinhan, et al.
Published: (2025)
Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
by: Ge, Suyu, et al.
Published: (2023)
by: Ge, Suyu, et al.
Published: (2023)
Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression
by: Liu, Peiyu, et al.
Published: (2024)
by: Liu, Peiyu, et al.
Published: (2024)
KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head
by: Rehg, Isaac
Published: (2024)
by: Rehg, Isaac
Published: (2024)
EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
by: Ji, Shiyu, et al.
Published: (2026)
by: Ji, Shiyu, et al.
Published: (2026)
NestedKV: Nested Memory Routing for Long-Context KV Cache Compression
by: Chen, Hong, et al.
Published: (2026)
by: Chen, Hong, et al.
Published: (2026)
CaliDrop: KV Cache Compression with Calibration
by: Su, Yi, et al.
Published: (2025)
by: Su, Yi, et al.
Published: (2025)
ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection
by: Datta, Debajyoti, et al.
Published: (2026)
by: Datta, Debajyoti, et al.
Published: (2026)
Lossless KV Cache Compression to 2%
by: Yang, Zhen, et al.
Published: (2024)
by: Yang, Zhen, et al.
Published: (2024)
Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding
by: Chen, Yifang, et al.
Published: (2025)
by: Chen, Yifang, et al.
Published: (2025)
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
by: Liu, Xiang, et al.
Published: (2025)
by: Liu, Xiang, et al.
Published: (2025)
EvolKV: Evolutionary KV Cache Compression for LLM Inference
by: Yu, Bohan, et al.
Published: (2025)
by: Yu, Bohan, et al.
Published: (2025)
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
by: Cai, Zefan, et al.
Published: (2024)
by: Cai, Zefan, et al.
Published: (2024)
Stateful KV Cache Management for LLMs: Balancing Space, Time, Accuracy, and Positional Fidelity
by: Poudel, Pratik
Published: (2025)
by: Poudel, Pratik
Published: (2025)
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
by: Peng, Junjie, et al.
Published: (2026)
by: Peng, Junjie, et al.
Published: (2026)
G-KV: Decoding-Time KV Cache Eviction with Global Attention
by: Liao, Mengqi, et al.
Published: (2025)
by: Liao, Mengqi, et al.
Published: (2025)
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
by: Cai, Zefan, et al.
Published: (2025)
by: Cai, Zefan, et al.
Published: (2025)
KVSculpt: KV Cache Compression as Distillation
by: Jiang, Bo, et al.
Published: (2026)
by: Jiang, Bo, et al.
Published: (2026)
KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs
by: Chen, Jian, et al.
Published: (2026)
by: Chen, Jian, et al.
Published: (2026)
EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
by: Cheong, Minsoo, et al.
Published: (2026)
by: Cheong, Minsoo, et al.
Published: (2026)
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
by: Du, Wenjie, et al.
Published: (2025)
by: Du, Wenjie, et al.
Published: (2025)
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
by: Liu, Akide, et al.
Published: (2024)
by: Liu, Akide, et al.
Published: (2024)
PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
by: An, Zihao, et al.
Published: (2026)
by: An, Zihao, et al.
Published: (2026)
TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Games
by: Mishra, Prakamya, et al.
Published: (2025)
by: Mishra, Prakamya, et al.
Published: (2025)
Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques
by: Javidnia, Neusha, et al.
Published: (2025)
by: Javidnia, Neusha, et al.
Published: (2025)
SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
by: Wu, Shunlong, et al.
Published: (2026)
by: Wu, Shunlong, et al.
Published: (2026)
CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models
by: Liang, Yihao, et al.
Published: (2026)
by: Liang, Yihao, et al.
Published: (2026)
Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression
by: Kriuk, Boris, et al.
Published: (2025)
by: Kriuk, Boris, et al.
Published: (2025)
Similar Items
-
AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection
by: Ray, Pretam, et al.
Published: (2026) -
SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers
by: Manem, Chaitanya, et al.
Published: (2025) -
Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks
by: Wang, Jianghui, et al.
Published: (2025) -
DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
by: Singh, Aditya Kumar, et al.
Published: (2026) -
X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression
by: Li, Guihong, et al.
Published: (2025)