# HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference

arXiv: https://arxiv.org/abs/2502.03589 · HTML: https://mlsanity.com/paper/2502.03589/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [D'ej`aVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving](https://mlsanity.com/paper/2403.01876/) (2024)
- [Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration](https://mlsanity.com/paper/2405.16546/) (2024)

## Built on by (most cited first, 10 of 10)

- [KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving](https://mlsanity.com/paper/2605.13734/) (2026)
- [Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven](https://mlsanity.com/paper/2605.06014/) (2026)
- [DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce](https://mlsanity.com/paper/2602.08923/) (2026)
- [Runtime-Certified Bounded-Error Quantized Attention](https://mlsanity.com/paper/2605.20868/) (2026)
- [SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer](https://mlsanity.com/paper/2607.28150/) (2026)
- [Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference](https://mlsanity.com/paper/2607.01831/) (2026)
- [Entropy-Constrained Adaptive Stochastic Quantization](https://mlsanity.com/paper/2608.18147/) (2026)
- [UltraSketchLLM: Sub-1-Bit LLM Compression via Sketch and Hardware-Friendly Operators](https://mlsanity.com/paper/2506.17255/) (2025)
- [Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management](https://mlsanity.com/paper/2609.06940/) (2026)
- [TORQUE: Optimizing What (not) to Quantize Before and After Rotation](https://mlsanity.com/paper/2609.36032/) (2026)

## Abstract (arXiv)

Disaggregated Large Language Model (LLM) inference has gained popularity as it separates the computation-intensive prefill stage from the memory-intensive decode stage, avoiding the prefill-decode interference and improving resource utilization. However, transmitting Key-Value (KV) data between the two stages can be a bottleneck, especially for long prompts. Additionally, the computation time overhead for prefill and decode is key for optimizing Job Completion Time (JCT), and KV data size can become prohibitive for long prompts and sequences. Existing KV quantization methods can alleviate the transmission bottleneck and reduce memory requirements, but they introduce significant dequantization overhead, exacerbating the computation time. We propose Homomorphic Acceleration via Compression of the KV cache (HACK) for disaggregated LLM inference. HACK eliminates the heavy KV dequantization step, and directly performs computations on quantized KV data to approximate and reduce the cost of the expensive matrix-multiplication step. Extensive trace-driven experiments show that HACK reduces JCT by up to 70.9% compared to disaggregated LLM inference baseline and by up to 52.3% compared to state-of-the-art KV quantization methods.