Challenge: Existing methods to evict KV cache during inference phase are impractical for industrial-grade applications.
Approach: They propose a method that combines token-wise KV cache eviction with PagedAttention and propose 'zipage' it achieves 95% of the performance of Full KV inference engines while delivering over 2.1 speedup .
Outcome: The proposed method achieves 95% of the performance of Full KV inference engines while delivering over 2.1 speedup on large-scale mathematical reasoning tasks.

Similar Papers

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are exploding to large sizes, including GPT, LLaMA, and DeepSeek.
Approach: They propose a fine-grained, structured KV cache pruning strategy that enhances the memory efficiency of vLLM’s PagedAttention.
Outcome: The proposed method integrates seamlessly with PagedAttention without any modifications to its CUDA attention kernels.
LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing KV cache compression methods mitigate memory bottlenecks but struggle in long reasoning tasks.
Approach: They propose a lagged eviction framework that prioritizes evicts based on tokens’ recurrence patterns to reduce KV cache by 50% and maintain comparable accuracy.
Outcome: The proposed framework reduces KV cache by 50% 70% while maintaining comparable accuracy, outperforming existing KV baselines.
HqeKV: Towards Hybrid Quantization and Eviction for KV Cache in Long-Context LLM Inference (2026.findings-acl)

Copied to clipboard

Challenge: autoregressive inference requires repeated computation across transformer layers.
Approach: They propose a hybrid compression framework built on both quantization and eviction . they propose varying importance metric and flexible conversion policies to reduce memory overhead .
Outcome: The proposed framework outperforms state-of-the-art methods under memory constraints.
NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) with extended context windows are expensive and infeasible on fixed memory hardware due to the surprisingly large memory consumption of KV Cache.
Approach: They propose a general framework for long-context KV cache eviction that achieves more optimal and efficient evict in a single operation during the encoding phase.
Outcome: The proposed framework improves performance on short- and long-text tasks by 80% and 76% respectively, reducing KV Cache by up to 5 with over 95% performance maintenance.
ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty (2025.coling-main)

Copied to clipboard

Challenge: Existing methods to accelerate inference of Large Language models (LLMs) are limited in their ability to retain key tokens as input length increases.
Approach: They propose a method that leverages layer uncertainty to allocate budget size for each layer to reduce memory usage.
Outcome: The proposed method reduces memory usage of the KV caches to only 20% when compared to full KV inference while achieving nearly lossless performance.
Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query (2025.emnlp-main)

Copied to clipboard

Challenge: Existing KV cache eviction methods prune tokens using prefilling-stage attention scores, causing inconsistency with actual inference queries.
Approach: They propose a lookahead q-cache framework that generates low-cost pseudo lookaheaded queries to better approximate the true decoding-stage queries.
Outcome: The proposed framework outperforms existing methods on LongBench and Needle-in-a-Haystack benchmarks and can be flexibly combined to yield further improvements.
Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models face quadratic computational costs, information forgetting, and context fragmentation . current methodologies diverge into three paradigms, each facing inherent trade-offs between Equal contribution.
Approach: They propose a framework that enables efficient long-context inference via chunk-wise compression and selective memory recall.
Outcome: The proposed framework reduces peak GPU memory usage and speeds up inference on multi-hop reasoning benchmarks.
FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference (2025.findings-emnlp)

Copied to clipboard

Challenge: Key-Value (KV) cache reading latency increases with context lengths hindering LLM inference . important tokens are sparsely distributed across the long context, making existing retrieval inaccurate .
Approach: They propose a method to retain a small fraction of KV cache based on token importance . important tokens are often sparsely distributed across the long context .
Outcome: The proposed method reduces decoding latency by 1.2 to 1.5.
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches (2024.findings-emnlp)

Copied to clipboard

Challenge: Long context capability is a crucial competency for large language models as it mitigates the human struggle to digest long-form texts.
Approach: They propose to evaluate 10+ state-of-the-art approaches for long context-capable LLMs.
Outcome: The proposed methods are compared against 10+ state-of-the-art approaches across seven categories of long context tasks.
More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression (2025.findings-emnlp)

Copied to clipboard

Challenge: storing more tokens in the KV cache at lower precision can enhance the long-context performance of large language models.
Approach: They propose a token-precision trade-off strategy to optimize KV cache compression . they also propose storing more tokens in the KV at lower precision .
Outcome: The proposed method achieves an optimal point within the Information Bottleneck compared to standalone KV pruning or KV quantization.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations