Event-Driven Language Models with Sparse Neural Activity for Neuromorphic Hardware

• URL: http://arxiv.org/abs/2608.30439v1
• Date: Mon, 31 Aug 2026 08:28:01 GMT
• Title: Event-Driven Language Models with Sparse Neural Activity for Neuromorphic Hardware
• Abstract summary: Inference with transformer-based large language models (LLMs) is often limited by the memory-bound KV cache and quadratic attention cost.<n>We introduce a method that induces sparse neural activity in heavily quantized linear-attention models with minimal performance loss.
• Score: 5.066906328188419
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inference with transformer-based large language models (LLMs) is often limited by the memory-bound KV cache and quadratic attention cost. State-space models (SSMs) mitigate this through linear attention and fixed-size recurrent states, but their large dense linear projections remain computationally expensive even after quantization. We introduce a method that induces sparse neural activity in heavily quantized linear-attention models with minimal performance loss. Activations below a per-projection trainable threshold ($\pm Δ$) are nullified while preserving crucial outliers, achieving comparable performance to dense models with up to 4$\times$ fewer effective arithmetic operations. Targeting a multi-core, multi-chip neuromorphic platform, where event-driven execution converts unstructured sparsity into throughput at both the compute and communication levels, a capability GPU architectures fundamentally lack, we project up to 37$\times$ higher throughput and 16$\times$ lower power versus edge GPU inference of a comparable transformer-based model, and up to 5.4$\times$ improvements over the non-sparsified baseline. These results position sparse, quantized linear-attention models as a natural fit for deploying LLMs on event-driven multi-core platforms.

Related papers

• M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling [53.351103753419046]
  We introduce Matrix-to-Matrix RNN: an architecture with matrix-valued hidden states and expressive non-linear state transitions.<n>We demonstrate that the language modeling performance of non-linear RNNs is limited by their state size.<n>We also demonstrate how the state size expansion mechanism enables efficient use of tensor cores.
  arXiv  Detail & Related papers  (2026-03-15T12:53:09Z)
• The Curious Case of In-Training Compression of State Space Models [49.819321766705514]
  State Space Models (SSMs) tackle long sequence modeling tasks efficiently, offer both parallelizable training and fast inference.<n>Key design challenge is striking the right balance between maximizing expressivity and limiting this computational burden.<n>Our approach, textscCompreSSM, applies to Linear Time-Invariant SSMs such as Linear Recurrent Units, but is also extendable to selective models.
  arXiv  Detail & Related papers  (2025-10-03T09:02:33Z)
• Analog Foundation Models [8.881648853584165]
  Analog in-memory computing (AIMC) is a promising compute paradigm to improve speed and power efficiency of neural network computations.<n>AIMC introduces fundamental challenges such as noisy computations and strict inference on input and quantization.<n>We introduce a general scalable method to robustly adapt and execute on low-precision analog hardware.
  arXiv  Detail & Related papers  (2025-05-14T14:52:22Z)
• DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding [26.39397960987363]
  We propose a simple modification to pretrained transformer models.<n>Instead of concatenation with the language prompt at the start, we insert multimodal tokens directly into the middle.<n>Our results indicate that our method reduces computational costs during both training and inference.
  arXiv  Detail & Related papers  (2025-04-27T18:56:26Z)
• 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)
• CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation [19.447967755388092]
  We propose CoLA and its memory-efficient implementation, CoLA-M, to replace full-size layers with compute-efficient auto-encoders.<n>Experiments on LLaMA models with 60 million to 7 billion parameters show that CoLA reduces the computing cost by $bf 2pmbtimes$.<n>CoLA-M further squeezes memory cost without sacrificing throughput, offering a pre-training approach with collectively superior parameter, computing, and memory efficiency.
  arXiv  Detail & Related papers  (2025-02-16T01:05:16Z)
• Linearizing Large Language Models [26.94551511277412]
  We present a method to uptrain existing large pre-trained transformers into Recurrent Neural Networks (RNNs) with a modest compute budget. We find that our linearization technique leads to competitive performance on standard benchmarks, but we identify persistent in-context learning and long-context modeling shortfalls for even the largest linear models.
  arXiv  Detail & Related papers  (2024-05-10T17:59:08Z)
• FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs [9.072821427818557]
  Large Language Models (LLMs) have achieved state-of-the-art performance across various language tasks but pose challenges for practical deployment. We propose an efficient weight-only quantization method that reduces memory consumption and accelerates inference for LLMs. We evaluate our approach on large-scale open source models such as OPT-175B and internal MoE models, showcasing minimal accuracy loss while achieving up to 3.65 times higher throughput.
  arXiv  Detail & Related papers  (2023-08-16T23:57:41Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• Efficient Long Sequence Modeling via State Space Augmented Transformer [92.74707853711374]
  We propose SPADE, short for $underlinetextbfS$tate sunderlinetextbfP$ace. We augment a SSM into the bottom layer of SPADE, and we employ efficient local attention methods for the other layers. Experimental results on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-12-15T20:51:27Z)
• Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints [59.39280540478479]
  We propose sparse upcycling -- a simple way to reuse sunk training costs by initializing a sparsely activated Mixture-of-Experts model from a dense checkpoint. We show that sparsely upcycled T5 Base, Large, and XL language models and Vision Transformer Base and Large models, respectively, significantly outperform their dense counterparts on SuperGLUE and ImageNet.
  arXiv  Detail & Related papers  (2022-12-09T18:57:37Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)
• LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models [9.727062803700264]
  We introduce LUT-GEMM, an efficient kernel for quantized matrix multiplication. LUT-GEMM eliminates the resource-intensive dequantization process and reduces computational costs. We show experimentally that when applied to the OPT-175B model with 3-bit quantization, LUT-GEMM substantially accelerates token generation latency.
  arXiv  Detail & Related papers  (2022-06-20T03:48:17Z)

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.