Sparser, Faster, Lighter Transformer Language Models

• URL: http://arxiv.org/abs/2603.23198v1
• Date: Tue, 24 Mar 2026 13:43:27 GMT
• Title: Sparser, Faster, Lighter Transformer Language Models
• Abstract summary: Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs.<n>We tackle these costs by leveraging unstructured sparsity within an LLM's feedforward layers.<n>We release all code and kernels under an open-source license to promote adoption and accelerate research toward establishing sparsity as a practical axis.
• Score: 14.129727529605367
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, we tackle these costs by leveraging unstructured sparsity within an LLM's feedforward layers, the components accounting for most of the model parameters and execution FLOPs. To achieve this, we introduce a new sparse packing format and a set of CUDA kernels designed to seamlessly integrate with the optimized execution pipelines of modern GPUs, enabling efficient sparse computation during LLM inference and training. To substantiate our gains, we provide a quantitative study of LLM sparsity, demonstrating that simple L1 regularization can induce over 99% sparsity with negligible impact on downstream performance. When paired with our kernels, we show that these sparsity levels translate into substantial throughput, energy efficiency, and memory usage benefits that increase with model scale. We will release all code and kernels under an open-source license to promote adoption and accelerate research toward establishing sparsity as a practical axis for improving the efficiency and scalability of modern foundation models.

Related papers

• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• Language Ranker: A Lightweight Ranking framework for LLM Decoding [70.01564145836129]
  This paper conceptualizes the decoding process as analogous to the ranking stage in recommendation pipelines.<n>Motivated by this insight, we propose Language Ranker, a novel framework that introduces a lightweight module to rerank candidate responses.<n> Experiments show that Language Ranker achieves performance comparable to large-scale reward models, while requiring only 0.5M additional parameters.
  arXiv  Detail & Related papers  (2025-10-23T17:56:46Z)
• 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)
• From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs [23.253571170594455]
  Large Language Models (LLMs) have significantly advanced artificial intelligence.<n>This paper introduces a three-stage cost-efficient end-to-end LLM deployment pipeline.<n>It produces super-tiny online models with enhanced performance and reduced costs.
  arXiv  Detail & Related papers  (2025-04-18T05:25:22Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [86.76714527437383]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• Explore Activation Sparsity in Recurrent LLMs for Energy-Efficient Neuromorphic Computing [3.379854610429579]
  Recurrent Large Language Models (R-LLM) have proven effective in mitigating the complexity of self-attention.<n>We propose a low-cost, training-free algorithm to sparsify R-LLMs' activations to enhance energy efficiency on neuromorphic hardware.
  arXiv  Detail & Related papers  (2025-01-09T19:13:03Z)
• 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)
• eFedLLM: Efficient LLM Inference Based on Federated Learning [1.6179784294541053]
  Large Language Models (LLMs) herald a transformative era in artificial intelligence (AI) This paper introduces an effective approach that enhances the operational efficiency and affordability of LLM inference.
  arXiv  Detail & Related papers  (2024-11-24T22:50:02Z)
• Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs [75.11449420928139]
  Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. Low-Rank Adaptation (LoRA) has emerged as a promising solution, but there exists a gap between the practical performance of low-rank adaptations and its theoretical optimum. We propose eXtreme Gradient Boosting LoRA, a novel framework that bridges this gap by leveraging the power of ensemble learning.
  arXiv  Detail & Related papers  (2024-10-25T17:07:13Z)
• 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)
• One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models [42.95555008229016]
  We propose a method based on Hessian sensitivity-aware mixed sparsity pruning to prune LLMs to at least 50% sparsity without the need of any retraining. The advantages of the proposed method exhibit even more when the sparsity is extremely high.
  arXiv  Detail & Related papers  (2023-10-14T05:43:09Z)

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.