# Reimagining Memory Access for LLM Inference: Compression-Aware Memory Controller Design

arXiv: https://arxiv.org/abs/2503.18869 · HTML: https://mlsanity.com/paper/2503.18869/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 29 of 29)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [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)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [Mixture-of-Depths: Dynamically allocating compute in transformer-based language models](https://mlsanity.com/paper/2404.02258/) (2024)
- [Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time](https://mlsanity.com/paper/2310.17157/) (2023)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [LLM in a flash: Efficient Large Language Model Inference with Limited Memory](https://mlsanity.com/paper/2312.11514/) (2023)
- [LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training](https://mlsanity.com/paper/2406.16554/) (2024)
- [RPTQ: Reorder-based Post-training Quantization for Large Language Models](https://mlsanity.com/paper/2304.01089/) (2023)
- [KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization](https://mlsanity.com/paper/2405.03917/) (2024)
- [Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs](https://mlsanity.com/paper/2402.10517/) (2024)
- [EBPC: Extended Bit-Plane Compression for Deep Neural Network Inference and Training Accelerators](https://mlsanity.com/paper/1908.11645/) (2019)
- [SmartQuant: CXL-based AI Model Store in Support of Runtime Configurable Weight Quantization](https://mlsanity.com/paper/2407.15866/) (2024)
- [ZipCache: A DRAM/SSD Cache with Built-in Transparent Compression](https://mlsanity.com/paper/2411.03174/) (2024)

## Built on by (most cited first, 5 of 5)

- [Gated Differentiable Working Memory for Long-Context Language Modeling](https://mlsanity.com/paper/2601.12906/) (2026)
- [CCF: A Context Compression Framework for Efficient Long-Sequence Language Modeling](https://mlsanity.com/paper/2509.09199/) (2025)
- [Joint Encoding of KV-Cache Blocks for Scalable LLM Serving](https://mlsanity.com/paper/2601.03067/) (2026)
- [DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression](https://mlsanity.com/paper/2607.06523/) (2026)
- [Read What Matters: Query-Adaptive Quantization for KV Caches](https://mlsanity.com/paper/2610.11245/) (2026)

## Abstract (arXiv)

The efficiency of Large Language Model~(LLM) inference is often constrained by substantial memory bandwidth and capacity demands. Existing techniques, such as pruning, quantization, and mixture of experts/depth, reduce memory capacity and/or bandwidth consumption at the cost of slight degradation in inference quality. This paper introduces a design solution that further alleviates memory bottlenecks by enhancing the on-chip memory controller in AI accelerators to achieve two main objectives: (1) significantly reducing memory capacity and bandwidth usage through lossless block compression~(e.g., LZ4 and ZSTD) of model weights and key-value (KV) cache without compromising inference quality, and (2) enabling memory bandwidth and energy consumption to scale proportionally with context-dependent dynamic quantization. These goals are accomplished by equipping the on-chip memory controller with mechanisms to improve fine-grained bit-level accessibility and compressibility of weights and KV cache through LLM-aware configuration of in-memory placement and representation. Experimental results on publicly available LLMs demonstrate the effectiveness of this approach, showing memory footprint reductions of 25.2% for model weights and 46.9% for KV cache. In addition, our hardware prototype at 4,GHz and 32 lanes (7,nm) achieves 8,TB/s throughput with a modest area overhead (under 3.8,mm(2)), which underscores the viability of LLM-aware memory control as a key to efficient large-scale inference.