# R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference

arXiv: https://arxiv.org/abs/2504.19449 · HTML: https://mlsanity.com/paper/2504.19449/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 50 of its 54 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Placed in

- Efficient LLM inference and serving / [Early exit and edge inference](https://mlsanity.com/inference/early-exit-and-edge-inference/)

## Builds on (most cited first, 30 of 50)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [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)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)

## Built on by (most cited first, 21 of 21)

- [Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity](https://mlsanity.com/paper/2505.14884/) (2025)
- [DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs](https://mlsanity.com/paper/2506.20194/) (2025)
- [Spark Transformer: Reactivating Sparsity in FFN and Attention](https://mlsanity.com/paper/2506.06644/) (2025)
- [Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity](https://mlsanity.com/paper/2505.07239/) (2025)
- [Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation](https://mlsanity.com/paper/2604.00821/) (2026)
- [WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference](https://mlsanity.com/paper/2505.19427/) (2025)
- [GLASS: Global-Local Aggregation for Inference-time Sparsification of LLMs](https://mlsanity.com/paper/2508.14302/) (2025)
- [Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches](https://mlsanity.com/paper/2509.22166/) (2025)
- [Enabling Dynamic Sparsity in Quantized LLM Inference](https://mlsanity.com/paper/2511.04477/) (2025)
- [Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity](https://mlsanity.com/paper/2602.00397/) (2026)
- [WiSparse: Boosting LLM Inference Efficiency with Weight-Aware Mixed Activation Sparsity](https://mlsanity.com/paper/2602.14452/) (2026)
- [ActTail: Global Activation Sparsity in Large Language Models](https://mlsanity.com/paper/2603.12272/) (2026)
- [Masked Gated Linear Unit](https://mlsanity.com/paper/2506.23225/) (2025)
- [Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity](https://mlsanity.com/paper/2512.12744/) (2025)
- [Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs](https://mlsanity.com/paper/2607.27591/) (2026)
- [Celty: SpMSpV GPU Kernel and SIMT Co-Design for Efficient Dual-Sparse LLM Inference](https://mlsanity.com/paper/2608.01536/) (2026)
- [Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization](https://mlsanity.com/paper/2608.12953/) (2026)
- [Model Casting and Low-Parameter Gating: Towards More Sparsely Activated FFNs](https://mlsanity.com/paper/2609.31975/) (2026)
- [Where Activation Sparsity and KV-Cache Sparsity Cross in LLM Decoding](https://mlsanity.com/paper/2609.33889/) (2026)
- [Activation Sparsity with Weight Approximation for Faster LLM Decoding on Offloaded Weights](https://mlsanity.com/paper/2610.02598/) (2026)
- [How Many Ranks Does a Token Need? A Noise-Floor Squelch for Rank-One LoRA Experts](https://mlsanity.com/paper/2610.19033/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs), while demonstrating remarkable capabilities across various applications, present significant challenges during inference due to their substantial model size, especially when deployed on edge devices. Activation sparsity offers a promising solution to reduce computation and memory movement, enabling more efficient inference, particularly for small-batch on-device applications. However, current approaches face limitations with non-ReLU activation function, which are foundational to most advanced LLMs, or require heavy continual training. Additionally, the difficulty in predicting active channels and limited achievable sparsity ratios constrain the effectiveness of activation sparsity-based methods. In this paper, we introduce R-Sparse, a training-free activation sparsity approach capable of achieving high sparsity levels in advanced LLMs. We conducted two preliminary investigations into how different components contribute to the output within a single linear layer and found two key observations: (i) the non-sparse components of the input function can be regarded as a few bias terms, and (ii) The full computation can be effectively approximated by an appropriate combination of input channels and weight singular values. Building on this, we replace the linear layers in LLMs with a rank-aware sparse inference method that leverages the sparsity of input channels and singular value components, eliminating the need for active channel prediction like the output sparsity based approaches. Experiments on Llama-2/3 and Mistral models across ten diverse tasks demonstrate that R-Sparse achieves comparable performance at 50% model-level sparsity, resulting in a significant 43% end-to-end efficient improvements with customized kernels.