# AlignPred: Error-Controlled KV Cache Compression via Alignment and Predictive Coding

arXiv: https://arxiv.org/abs/2610.17970 · HTML: https://mlsanity.com/paper/2610.17970/

## 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 24 of its 39 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [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)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention](https://mlsanity.com/paper/2403.19708/) (2024)
- [Reducing Transformer Key-Value Cache Size with Cross-Layer Attention](https://mlsanity.com/paper/2405.12981/) (2024)
- [LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference](https://mlsanity.com/paper/2510.09665/) (2025)
- [MiniCache: KV Cache Compression in Depth Dimension for Large Language Models](https://mlsanity.com/paper/2405.14366/) (2024)
- [TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate](https://mlsanity.com/paper/2504.19874/) (2025)
- [KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization](https://mlsanity.com/paper/2405.03917/) (2024)
- [Palu: Compressing KV-Cache with Low-Rank Projection](https://mlsanity.com/paper/2407.21118/) (2024)
- [SZ3: A Modular Framework for Composing Prediction-Based Error-Bounded Lossy Compressors](https://mlsanity.com/paper/2111.02925/) (2021)
- [InferCept: Efficient Intercept Support for Augmented Large Language Model Inference](https://mlsanity.com/paper/2402.01869/) (2024)
- [LongBench Pro: A More Realistic and Comprehensive Bilingual Long-Context Evaluation Benchmark](https://mlsanity.com/paper/2601.02872/) (2026)
- [cuSZ: An Efficient GPU-Based Error-Bounded Lossy Compression Framework for Scientific Data](https://mlsanity.com/paper/2007.09625/) (2020)
- [xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction](https://mlsanity.com/paper/2503.18893/) (2025)
- [KV Cache Transform Coding for Compact Storage in LLM Inference](https://mlsanity.com/paper/2511.01815/) (2025)
- [KVComp: A High-Performance, LLM-Aware, Lossy Compression Framework for KV Cache](https://mlsanity.com/paper/2509.00579/) (2025)
- [PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression](https://mlsanity.com/paper/2512.24449/) (2025)
- [Efficient Remote KV Cache Reuse with GPU-native Video Codec](https://mlsanity.com/paper/2602.09725/) (2026)

## Abstract (arXiv)

Long-running agents retain KV caches across turns and sessions for hours or days. Compressing these persistent caches requires reducing storage while controlling reconstruction error. We present AlignPred, a codec that combines local alignment with predictive coding under a configurable KV reconstruction-error budget. Local orthogonal transforms align related heads or layers into a common coordinate frame, allowing AlignPred to combine token-wise prediction with same-token prediction across heads or layers. Residuals are quantized on an error-bounded lattice and entropy-coded, without learned predictors, encoder-side mode search, or large joint transforms. Across three attention mechanisms, AlignPred requires less storage than the evaluated baselines at comparable measured reconstruction error. Against the evaluated CPU codec implementations, it decodes at least 1.6 times faster while matching or improving encode time. AlignPred achieves near-native task scores at substantially compressed operating points on LongBench-Pro at 128K context. AlignPred's SGLang HiCache integration reduces persistent target-KV storage by 42-72% relative to native HiCache, with comparable latency.