EfficientLLM: Efficiency in Large Language Models

• URL: http://arxiv.org/abs/2505.13840v1
• Date: Tue, 20 May 2025 02:27:08 GMT
• Title: EfficientLLM: Efficiency in Large Language Models
• Authors: Zhengqing Yuan, Weixiang Sun, Yixin Liu, Huichi Zhou, Rong Zhou, Yiyang Li, Zheyuan Zhang, Wei Song, Yue Huang, Haolong Jia, Keerthiram Murugesan, Yu Wang, Lifang He, Jianfeng Gao, Lichao Sun, Yanfang Ye,
• Abstract summary: Large Language Models (LLMs) have driven significant progress, yet their growing counts and context windows incur prohibitive compute, energy, and monetary costs.<n>We introduce EfficientLLM, a novel benchmark and the first comprehensive empirical study evaluating efficiency techniques for LLMs at scale.
• Score: 64.3537131208038
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have driven significant progress, yet their growing parameter counts and context windows incur prohibitive compute, energy, and monetary costs. We introduce EfficientLLM, a novel benchmark and the first comprehensive empirical study evaluating efficiency techniques for LLMs at scale. Conducted on a production-class cluster (48xGH200, 8xH200 GPUs), our study systematically explores three key axes: (1) architecture pretraining (efficient attention variants: MQA, GQA, MLA, NSA; sparse Mixture-of-Experts (MoE)), (2) fine-tuning (parameter-efficient methods: LoRA, RSLoRA, DoRA), and (3) inference (quantization methods: int4, float16). We define six fine-grained metrics (Memory Utilization, Compute Utilization, Latency, Throughput, Energy Consumption, Compression Rate) to capture hardware saturation, latency-throughput balance, and carbon cost. Evaluating over 100 model-technique pairs (0.5B-72B parameters), we derive three core insights: (i) Efficiency involves quantifiable trade-offs: no single method is universally optimal; e.g., MoE reduces FLOPs and improves accuracy but increases VRAM by 40%, while int4 quantization cuts memory/energy by up to 3.9x at a 3-5% accuracy drop. (ii) Optima are task- and scale-dependent: MQA offers optimal memory-latency trade-offs for constrained devices, MLA achieves lowest perplexity for quality-critical tasks, and RSLoRA surpasses LoRA efficiency only beyond 14B parameters. (iii) Techniques generalize across modalities: we extend evaluations to Large Vision Models (Stable Diffusion 3.5, Wan 2.1) and Vision-Language Models (Qwen2.5-VL), confirming effective transferability. By open-sourcing datasets, evaluation pipelines, and leaderboards, EfficientLLM provides essential guidance for researchers and engineers navigating the efficiency-performance landscape of next-generation foundation models.

Related papers

• Slimming Down LLMs Without Losing Their Minds [3.15067317204403]
  This paper investigates and validates the impact of fine-tuning on large language model performance, focusing on parameter-efficient methods (LoRA and QLoRA)<n>We evaluate model capabilities across three key domains: (1) commonsense reasoning (HellaSwag), (2) mathematical reasoning (GSM8K), and (3) multi-domain knowledge (MMLU-CS)
  arXiv  Detail & Related papers  (2025-06-12T16:49:40Z)
• MiniCPM4: Ultra-Efficient LLMs on End Devices [124.73631357883228]
  MiniCPM4 is a highly efficient large language model (LLM) designed explicitly for end-side devices.<n>We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.<n>MiniCPM4 is available in two versions, with 0.5B and 8B parameters, respectively.
  arXiv  Detail & Related papers  (2025-06-09T16:16:50Z)
• Harnessing On-Device Large Language Model: Empirical Results and Implications for AI PC [8.837470787975308]
  Large Language Models (LLMs) on edge devices offer significant privacy benefits.<n>These on-device LLMs inherently face performance limitations due to reduced model capacity and necessary compression techniques.<n>We introduce a systematic methodology -- encompassing model capability, development efficiency, and system resources -- for evaluating on-device LLMs.
  arXiv  Detail & Related papers  (2025-05-21T02:23:01Z)
• R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference [77.47238561728459]
  R-Sparse is a training-free activation sparsity approach capable of achieving high sparsity levels in advanced LLMs.<n> Experiments on Llama-2/3 and Mistral models across ten diverse tasks demonstrate that R-Sparse achieves comparable performance at 50% model-level sparsity.
  arXiv  Detail & Related papers  (2025-04-28T03:30:32Z)
• Structure-Activation Synergy: A Dual Efficiency Framework for Parameter-Memory Optimized Transfer Learning [8.602744958104969]
  We present Structure-Activation Synergy (S2A), an innovative framework achieving dual optimization of parameters and memory.<n>We show S2A's superior efficiency, reducing GPU memory consumption by 75% (4.2 average reduction) while maintaining 98.7% of full fine-tuning accuracy with only 0.9% tunable parameters.
  arXiv  Detail & Related papers  (2025-03-11T08:10:03Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• MOFHEI: Model Optimizing Framework for Fast and Efficient Homomorphically Encrypted Neural Network Inference [0.8388591755871735]
  Homomorphic Encryption (HE) enables us to perform machine learning tasks over encrypted data.<n>We propose MOFHEI, a framework that optimize the model to make HE-based neural network inference, fast and efficient.<n>Our framework achieves up to 98% pruning ratio on LeNet, eliminating up to 93% of the required HE operations for performing PI.
  arXiv  Detail & Related papers  (2024-12-10T22:44:54Z)
• LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization [17.190984773586745]
  Current AR-based visual generation models require substantial computational resources, limiting their applicability on resource-constrained devices. We propose efficient attention mechanism and low-bit quantization method to enhance the efficiency of VAR models while maintaining performance.
  arXiv  Detail & Related papers  (2024-11-26T07:32:36Z)
• Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention [27.46314600638108]
  We find that low-rank pre-training, normally considered as efficient methods, can be scalably effective when reduced parameters are precisely targeted. We refer to this structure as Low-dimensional Projected Attention (LPA) and provide an explanatory analysis. Our results show that LPA model can save up to 12.4% in time while achieving an approximate 5% improvement in test perplexity (ppl) and on downstream tasks compared with the vanilla Transformer.
  arXiv  Detail & Related papers  (2024-11-04T13:06:17Z)
• TernaryLLM: Ternarized Large Language Model [29.29122031050894]
  Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks. We introduce Dual Learnable Ternarization (DLT), which enables both scales and shifts to be learnable. We also propose Outlier-Friendly Feature Knowledge Distillation (OFF) to recover the information lost in extremely low-bit quantization.
  arXiv  Detail & Related papers  (2024-06-11T11:40:12Z)
• LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit [55.73370804397226]
  Quantization, a key compression technique, can effectively mitigate these demands by compressing and accelerating large language models. We present LLMC, a plug-and-play compression toolkit, to fairly and systematically explore the impact of quantization. Powered by this versatile toolkit, our benchmark covers three key aspects: calibration data, algorithms (three strategies), and data formats.
  arXiv  Detail & Related papers  (2024-05-09T11:49:05Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• RA-DIT: Retrieval-Augmented Dual Instruction Tuning [90.98423540361946]
  Retrieval-augmented language models (RALMs) improve performance by accessing long-tail and up-to-date knowledge from external data stores. Existing approaches require either expensive retrieval-specific modifications to LM pre-training or use post-hoc integration of the data store that leads to suboptimal performance. We introduce Retrieval-Augmented Dual Instruction Tuning (RA-DIT), a lightweight fine-tuning methodology that provides a third option.
  arXiv  Detail & Related papers  (2023-10-02T17:16:26Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.