# KVPruner: Structural Pruning for Faster and Memory-Efficient Large Language Models

arXiv: https://arxiv.org/abs/2409.11057 · HTML: https://mlsanity.com/paper/2409.11057/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 17 Sep 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [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)
- [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)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning](https://mlsanity.com/paper/2310.06694/) (2023)
- [Visual Dialog](https://mlsanity.com/paper/1611.08669/) (2016)
- [SSAST: Self-Supervised Audio Spectrogram Transformer](https://mlsanity.com/paper/2110.09784/) (2021)
- [PQCache: Product Quantization-based KVCache for Long Context LLM Inference](https://mlsanity.com/paper/2407.12820/) (2024)
- [Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods](https://mlsanity.com/paper/2402.02834/) (2024)
- [MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool](https://mlsanity.com/paper/2406.17565/) (2024)
- [UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers](https://mlsanity.com/paper/2303.00807/) (2023)
- [RDRec: Rationale Distillation for LLM-based Recommendation](https://mlsanity.com/paper/2405.10587/) (2024)
- [Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation](https://mlsanity.com/paper/2309.17352/) (2023)
- [Large-scale Language Model Rescoring on Long-form Data](https://mlsanity.com/paper/2306.08133/) (2023)

## Built on by (most cited first, 6 of 6)

- [EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models](https://mlsanity.com/paper/2502.06663/) (2025)
- [Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference](https://mlsanity.com/paper/2505.22913/) (2025)
- [SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging](https://mlsanity.com/paper/2603.14303/) (2026)
- [CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation](https://mlsanity.com/paper/2602.08686/) (2026)
- [The silence of the weights: a structural pruning strategy for attention-based audio signal architectures with second order metrics](https://mlsanity.com/paper/2509.26207/) (2025)
- [PatternKV: Flattening KV Representation Expands Quantization Headroom](https://mlsanity.com/paper/2510.05176/) (2025)

## Abstract (arXiv)

The bottleneck associated with the key-value(KV) cache presents a significant challenge during the inference processes of large language models. While depth pruning accelerates inference, it requires extensive recovery training, which can take up to two weeks. On the other hand, width pruning retains much of the performance but offers slight speed gains. To tackle these challenges, we propose KVPruner to improve model efficiency while maintaining performance. Our method uses global perplexity-based analysis to determine the importance ratio for each block and provides multiple strategies to prune non-essential KV channels within blocks. Compared to the original model, KVPruner reduces runtime memory usage by 50% and boosts throughput by over 35%. Additionally, our method requires only two hours of LoRA fine-tuning on small datasets to recover most of the performance.