# CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models

arXiv: https://arxiv.org/abs/2404.08763 · HTML: https://mlsanity.com/paper/2404.08763/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 68 references that are in the map.
- First posted on arXiv 12 Apr 2024.

## Builds on (most cited first, 30 of 56)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [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)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)
- [Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time](https://mlsanity.com/paper/2310.17157/) (2023)
- [Specializing Smaller Language Models towards Multi-Step Reasoning](https://mlsanity.com/paper/2301.12726/) (2023)
- [Hash Layers For Large Sparse Models](https://mlsanity.com/paper/2106.04426/) (2021)
- [MegaBlocks: Efficient Sparse Training with Mixture-of-Experts](https://mlsanity.com/paper/2211.15841/) (2022)

## Built on by (most cited first, 30 of 41)

- [PowerInfer-2: Fast Large Language Model Inference on a Smartphone](https://mlsanity.com/paper/2406.06282/) (2024)
- [Training-Free Activation Sparsity in Large Language Models](https://mlsanity.com/paper/2408.14690/) (2024)
- [HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference](https://mlsanity.com/paper/2411.01433/) (2024)
- [Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths](https://mlsanity.com/paper/2406.14909/) (2024)
- [Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters](https://mlsanity.com/paper/2406.05955/) (2024)
- [Sparsing Law: Towards Large Language Models with Greater Activation Sparsity](https://mlsanity.com/paper/2411.02335/) (2024)
- [R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference](https://mlsanity.com/paper/2504.19449/) (2025)
- [Instruction-Following Pruning for Large Language Models](https://mlsanity.com/paper/2501.02086/) (2025)
- [Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking](https://mlsanity.com/paper/2412.01380/) (2024)
- [Accelerating Transformer Inference and Training with 2:4 Activation Sparsity](https://mlsanity.com/paper/2503.16672/) (2025)
- [SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity](https://mlsanity.com/paper/2506.16500/) (2025)
- [Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models](https://mlsanity.com/paper/2505.01731/) (2025)
- [Scalable LLM Reasoning Acceleration with Low-rank Distillation](https://mlsanity.com/paper/2505.07861/) (2025)
- [Universal Properties of Activation Sparsity in Modern Large Language Models](https://mlsanity.com/paper/2509.00454/) (2025)
- [RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention](https://mlsanity.com/paper/2606.06256/) (2026)
- [Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity](https://mlsanity.com/paper/2505.14884/) (2025)
- [Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking](https://mlsanity.com/paper/2410.19274/) (2024)
- [Post-Training Statistical Calibration for Higher Activation Sparsity](https://mlsanity.com/paper/2412.07174/) (2024)
- [Spark Transformer: Reactivating Sparsity in FFN and Attention](https://mlsanity.com/paper/2506.06644/) (2025)
- [Sirius: Contextual Sparsity with Correction for Efficient LLMs](https://mlsanity.com/paper/2409.03856/) (2024)
- [HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs](https://mlsanity.com/paper/2502.00899/) (2025)
- [Prompt-based Depth Pruning of Large Language Models](https://mlsanity.com/paper/2502.04348/) (2025)
- [Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters](https://mlsanity.com/paper/2503.18216/) (2025)
- [WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference](https://mlsanity.com/paper/2505.19427/) (2025)
- [Negative Pre-activations Differentiate Syntax](https://mlsanity.com/paper/2509.24198/) (2025)
- [GLASS: Global-Local Aggregation for Inference-time Sparsification of LLMs](https://mlsanity.com/paper/2508.14302/) (2025)
- [VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking](https://mlsanity.com/paper/2511.18692/) (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)
- [Bug or Feature2: Weight Drift, Activation Sparsity and Spikes](https://mlsanity.com/paper/2605.17659/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have dramatically advanced AI applications, yet their deployment remains challenging due to their immense inference costs. Recent studies ameliorate the computational costs of LLMs by increasing their activation sparsity but suffer from significant performance degradation on downstream tasks. In this work, we introduce a new framework for sparsifying the activations of base LLMs and reducing inference costs, dubbed Contextually Aware Thresholding for Sparsity (CATS). CATS is relatively simple, easy to implement, and highly effective. At the heart of our framework is a new non-linear activation function. We demonstrate that CATS can be applied to various base models, including Mistral-7B and Llama2-7B, and outperforms existing sparsification techniques in downstream task performance. More precisely, CATS-based models often achieve downstream task performance within 1-2% of their base models without any fine-tuning and even at activation sparsity levels of 50%. Furthermore, CATS-based models converge faster and display better task performance than competing techniques when fine-tuning is applied. Finally, we develop a custom GPU kernel for efficient implementation of CATS that translates the activation of sparsity of CATS to real wall-clock time speedups. Our custom kernel implementation of CATS results in a ~15% improvement in wall-clock inference latency of token generation on both Llama-7B and Mistral-7B.