# Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy

arXiv: https://arxiv.org/abs/2606.09080 · HTML: https://mlsanity.com/paper/2606.09080/

## Key facts

- Cited by 4 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 21 of its 49 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## 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, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [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)
- [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)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [SliceGPT: Compress Large Language Models by Deleting Rows and Columns](https://mlsanity.com/paper/2401.15024/) (2024)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression](https://mlsanity.com/paper/2403.07378/) (2024)
- [SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference](https://mlsanity.com/paper/2502.18137/) (2025)
- [What Matters in Transformers? Not All Attention is Needed](https://mlsanity.com/paper/2406.15786/) (2024)
- [BlockPruner: Fine-grained Pruning for Large Language Models](https://mlsanity.com/paper/2406.10594/) (2024)
- [HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit](https://mlsanity.com/paper/2602.23699/) (2026)
- [From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models](https://mlsanity.com/paper/2601.18091/) (2026)
- [ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention](https://mlsanity.com/paper/2602.07574/) (2026)
- [UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking](https://mlsanity.com/paper/2602.23734/) (2026)
- [Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference](https://mlsanity.com/paper/2510.13831/) (2025)
- [ELANA: A Simple Energy and Latency Analyzer for LLMs](https://mlsanity.com/paper/2512.09946/) (2025)

## Built on by (most cited first, 4 of 4)

- [WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning](https://mlsanity.com/paper/2607.28418/) (2026)
- [MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs](https://mlsanity.com/paper/2610.01434/) (2026)
- [GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs](https://mlsanity.com/paper/2610.13035/) (2026)
- [Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs](https://mlsanity.com/paper/2610.18399/) (2026)

## Abstract (arXiv)

Pruning has emerged as a dominant paradigm for accelerating large language model (LLM) inference, spanning a broad spectrum of methods that remove computation across tokens, layers, heads, dimensions, and attention patterns. Despite sharing the same objective, these pruning approaches induce fundamentally different execution behaviors, causing realized speedups to depend heavily on hardware and kernel implementations. Consequently, the practical acceleration benefits of different pruning families remain poorly understood. In this work, we introduce a GEMM-centric taxonomy that reorganizes existing pruning methods according to the logical M, N, and K dimensions of general matrix multiplication (GEMM). Leveraging this abstraction, we build a unified benchmarking framework that enables implementation-consistent comparison across the pruning design space and systematically characterizes the acceleration--quality Pareto frontier. Our results on Llama3.1-8B show that static depth pruning remains the strongest Pareto-optimal baseline and stays closest to its theoretical acceleration upper bound in memory-bounded scenarios. During prefill, the frontier transitions from static depth at low quality loss (0%--4%), to dynamic depth at moderate loss (5%--16%), and finally to static width pruning at higher loss levels (17%--26%). These findings establish the first unified view of the practical limits of pruning-based LLM acceleration and provide guidance for future pruning research. Code is available at https://github.com/EIT-NLP/LLM-Pruning/tree/main/PruningInferSim