WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference

• URL: http://arxiv.org/abs/2505.19427v1
• Date: Mon, 26 May 2025 02:37:32 GMT
• Title: WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference
• Authors: Sihan Chen, Dan Zhao, Jongwoo Ko, Colby Banbury, Huiping Zhuang, Luming Liang, Tianyi Chen,
• Abstract summary: WINA (Weight Informed Neuron Activation) is a novel, simple, and training-free sparse activation framework.<n>We show that WINA obtains optimal approximation error bounds with theoretical guarantees tighter than existing techniques.<n>It also outperforms state-of-the-art methods (e.g., TEAL) by up to $2.94%$ in average performance at the same sparsity levels.
• Score: 44.538579135121466
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The growing computational demands of large language models (LLMs) make efficient inference and activation strategies increasingly critical. While recent approaches, such as Mixture-of-Experts (MoE), leverage selective activation but require specialized training, training-free sparse activation methods offer broader applicability and superior resource efficiency through their plug-and-play design. However, many existing methods rely solely on hidden state magnitudes to determine activation, resulting in high approximation errors and suboptimal inference accuracy. To address these limitations, we propose WINA (Weight Informed Neuron Activation), a novel, simple, and training-free sparse activation framework that jointly considers hidden state magnitudes and the column-wise $\ell_2$-norms of weight matrices. We show that this leads to a sparsification strategy that obtains optimal approximation error bounds with theoretical guarantees tighter than existing techniques. Empirically, WINA also outperforms state-of-the-art methods (e.g., TEAL) by up to $2.94\%$ in average performance at the same sparsity levels, across a diverse set of LLM architectures and datasets. These results position WINA as a new performance frontier for training-free sparse activation in LLM inference, advancing training-free sparse activation methods and setting a robust baseline for efficient inference. The source code is available at https://github.com/microsoft/wina.

Related papers

• ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining [53.893792844055106]
  Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency.<n>We introduce Selective Efficient Language Modeling, a risk-aware algorithm that improves training efficiency and distributional robustness by performing online token-level batch selection.<n> Experiments on GPT-2 pretraining show that ESLM significantly reduces training FLOPs while maintaining or improving both perplexity and downstream performance compared to baselines.
  arXiv  Detail & Related papers  (2025-05-26T12:23:26Z)
• CoLA: Collaborative Low-Rank Adaptation [3.421904493396495]
  Fine-tuning a pre-trained model for specific tasks achieves strong performance; however, it is computationally expensive and inefficient.<n>LoRA, in particular, has proven effective, but its application to multi-task scenarios is limited by interference between tasks.<n>We propose CoLA, a more flexible LoRA architecture and three collaborative strategies to enhance performance by better utilizing the quantitative relationships between $A$ and $B$.
  arXiv  Detail & Related papers  (2025-05-21T12:46:42Z)
• 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)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [53.571195477043496]
  We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE)<n>RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers.<n>Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
  arXiv  Detail & Related papers  (2025-02-13T06:44:33Z)
• Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models [14.68920095399595]
  sparsity-based PEFT (SPEFT) introduces trainable sparse adaptations to the weight matrices in the model.<n>We conduct the first systematic evaluation of salience metrics for SPEFT, inspired by zero-cost NAS proxies.<n>We compare static and dynamic masking strategies, finding that static masking, which predetermines non-zero entries before training, delivers efficiency without sacrificing performance.
  arXiv  Detail & Related papers  (2024-12-18T04:14:35Z)
• Activation Sparsity Opportunities for Compressing General Large Language Models [4.5624217435826]
  This work systematically investigates the tradeoff between enforcing activation sparsity and perplexity (accuracy) on state-of-the-art AI models.<n>Our empirical analysis demonstrates that we can obtain around 50% of main memory and computing reductions for critical FFN components with negligible accuracy degradation.
  arXiv  Detail & Related papers  (2024-12-13T02:26:54Z)
• Sparsing Law: Towards Large Language Models with Greater Activation Sparsity [62.09617609556697]
  Activation sparsity denotes the existence of substantial weakly-contributed elements within activation outputs that can be eliminated.<n>We propose PPL-$p%$ sparsity, a precise and performance-aware activation sparsity metric.<n>We show that ReLU is more efficient as the activation function than SiLU and can leverage more training data to improve activation sparsity.
  arXiv  Detail & Related papers  (2024-11-04T17:59:04Z)
• Search for Efficient Large Language Models [52.98684997131108]
  Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Weight pruning, quantization, and distillation have been embraced to compress LLMs, targeting memory reduction and inference acceleration. Most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures.
  arXiv  Detail & Related papers  (2024-09-25T21:32:12Z)
• Learn To be Efficient: Build Structured Sparsity in Large Language Models [17.940183066850565]
  Large Language Models (LLMs) have achieved remarkable success with their billion-level parameters, yet they incur high inference overheads.<n>Existing methods only focus on utilizing this naturally formed activation sparsity in a post-training setting.<n>We introduce a novel training algorithm, Learn-To-be-Efficient (LTE), designed to train efficiency-aware LLMs.
  arXiv  Detail & Related papers  (2024-02-09T01:18:16Z)

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.