# Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving

arXiv: https://arxiv.org/abs/2607.05399 · HTML: https://mlsanity.com/paper/2607.05399/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 30 of its 48 references that are in the map.
- First posted on arXiv 3 May 2026.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 30 of 30)

- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention](https://mlsanity.com/paper/2404.07143/) (2024)
- [You Only Cache Once: Decoder-Decoder Architectures for Language Models](https://mlsanity.com/paper/2405.05254/) (2024)
- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate](https://mlsanity.com/paper/2504.19874/) (2025)
- [ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification](https://mlsanity.com/paper/2405.14256/) (2024)
- [Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution](https://mlsanity.com/paper/2510.00636/) (2025)
- [QAQ: Quality Adaptive Quantization for LLM KV Cache](https://mlsanity.com/paper/2403.04643/) (2024)
- [Palu: Compressing KV-Cache with Low-Rank Projection](https://mlsanity.com/paper/2407.21118/) (2024)
- [LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy](https://mlsanity.com/paper/2410.03111/) (2024)
- [Compressed Context Memory For Online Language Model Interaction](https://mlsanity.com/paper/2312.03414/) (2023)
- [KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches](https://mlsanity.com/paper/2407.01527/) (2024)
- [KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing](https://mlsanity.com/paper/2410.18517/) (2024)
- [KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider](https://mlsanity.com/paper/2506.02634/) (2025)
- [Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs](https://mlsanity.com/paper/2404.10308/) (2024)
- [MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding](https://mlsanity.com/paper/2406.09297/) (2024)
- [LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference](https://mlsanity.com/paper/2503.08879/) (2025)
- [LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation](https://mlsanity.com/paper/2502.07365/) (2025)
- [Are Large Language Models the New Interface for Data Pipelines?](https://mlsanity.com/paper/2406.06596/) (2024)
- [KV Cache Compression for Inference Efficiency in LLMs: A Review](https://mlsanity.com/paper/2508.06297/) (2025)

## Abstract (arXiv)

Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks. This paper presents a workload-aware benchmark of representative KV-cache optimization mechanisms spanning quantization, pruning, and merging, including KIVI, TurboQuant, SnapKV, and CaM, evaluated on LongBench-style multi-document QA, single-document QA, few-shot learning, and summarization workloads using Llama-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3. The benchmark measures task quality, mean output throughput, mean time-to-first-token, and realized compression ratio across context-length buckets. The results show that the compression ratio alone is a poor predictor of end-to-end performance. KIVI4 provides the most stable quality across models, SnapKV delivers the strongest long-context throughput, and CaM yields large gains on selected QA workloads but exhibits substantial workload sensitivity in both quality and realized compression ratio. These findings motivate workload-aware selection of KV-cache mechanisms rather than one-size-fits-all compression and provide deployment guidance for long-context serving systems.