Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs

• URL: http://arxiv.org/abs/2607.27591v1
• Date: Thu, 30 Jul 2026 02:20:01 GMT
• Title: Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs
• Abstract summary: emphProx is a two-stage training-free framework for sparse SwiGLU FFNs.<n>It achieves up to a $1.99times$ end-to-end decoding speedup at 70% FFN sparsity.
• Score: 10.608163494702614
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Feed-forward networks (FFNs) dominate memory traffic and computation in large language model (LLM) inference, making them a primary target for activation sparsification. However, existing training-free methods suffer substantial model-quality degradation at high sparsity due to limitations in their channel-selection strategies. We observe that the SwiGLU intermediate state provides a highly effective channel-selection signal, but obtaining it requires costly dense computation. To address this, we present \emph{Prox}, a two-stage training-free framework for sparse SwiGLU FFNs. Prox hinges on the key insight: sparse execution requires only the channel mask induced by the intermediate state, which can be constructed from the magnitude ranking of its entries rather than their exact values. Specifically, Stage 1 uses input sparsity and quantized proxy weights to construct a shared mask; Stage 2 computes the selected channels exactly, enabling sparse execution of all three projections. Across ten LLMs from six model families, Prox outperforms training-free baselines at all sparsity levels, achieves up to a $1.99\times$ end-to-end decoding speedup at 70\% FFN sparsity, and is compatible with quantization and sparse attention.

Related papers

• LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models [56.999481798138625]
  LimiX-2M is a 2M- parameter model that outperforms larger TabPFN-v2 and TabICL baselines on widely used benchmarks.<n>We present a unified tokenize-and-route framework for strong Tabular foundation models (TFMs)<n>Results highlight value-aware tokenization and readout-aligned routing as key levers for improving the accuracy--efficiency trade-off in TFMs.
  arXiv  Detail & Related papers  (2026-06-03T06:07:33Z)
• Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders [123.58723804218151]
  Vision foundation models are bottlenecked by the quadratic cost of self-attention.<n>We present C-GSPN based on 2D spatial propagation propagation.
  arXiv  Detail & Related papers  (2026-05-30T14:29:43Z)
• SVD Contextual Sparsity Predictors for Fast LLM Inference [0.0]
  This paper presents a framework for accelerating inference of ReGLU-based feed-forward networks (FFNs) within large language models (LLMs)<n>Experiments demonstrate up to a 1.8x reduction in end-to-end decoding time while maintaining less than 1% degradation in benchmark scores on tasks involving complex math and code generation.
  arXiv  Detail & Related papers  (2026-03-14T20:36:13Z)
• WiSparse: Boosting LLM Inference Efficiency with Weight-Aware Mixed Activation Sparsity [32.61817486761883]
  Training-free activation sparsity is a promising approach for efficient Large Language Models inference.<n>We propose Weight-aware Mixed-Granularity Training-free Activation Sparsity (WiSparse)<n>We show that WiSparse preserves 97% of Llama3.1's dense performance, surpassing the strongest baseline by 2.23 percentage points.
  arXiv  Detail & Related papers  (2026-02-16T04:18:36Z)
• Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity [5.223181756178433]
  We introduce FastForward, a predictive sparsity framework that accelerates large language model (LLM) prefill through block-wise, context-aware FFN sparsity.<n>FastForward delivers up to 1.45$times$ compute-bound speedup at 50% FFN sparsity with $$ 6% accuracy loss compared to the dense baseline on LongBench.
  arXiv  Detail & Related papers  (2026-01-30T23:23:40Z)
• Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers [91.02299679350834]
  Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive.<n>We present Sparse--Dense Residual Fusion for Efficient Diffusion Transformers, a simple method that enables aggressive token dropping (up to 75%) while preserving quality.
  arXiv  Detail & Related papers  (2025-10-24T19:29:55Z)
• 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)
• Q-Sparse: All Large Language Models can be Fully Sparsely-Activated [93.45300714803429]
  We introduce Q-Sparse, a simple yet effective approach to training sparsely-activated large language models (LLMs) Q-Sparse enables full sparsity of activations in LLMs which can bring significant efficiency gains in inference. We also introduce Block Q-Sparse for batch training and inference.
  arXiv  Detail & Related papers  (2024-07-15T17:59:29Z)
• BiLLM: Pushing the Limit of Post-Training Quantization for LLMs [53.31402059062365]
  BiLLM is a groundbreaking 1-bit post-training quantization scheme tailored for pretrained large language models. It achieves for the first time high-accuracy inference (e.g. 8.41 perplexity on LLaMA2-70B) with only 1.08-bit weights across various LLMs families.
  arXiv  Detail & Related papers  (2024-02-06T09:26:34Z)
• QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models [44.515165695546614]
  Quantization-Aware Training (QAT) offers a solution, but its extensive training costs make Post-Training Quantization (PTQ) a more practical approach for Large Language Models (LLMs) We propose QLLM, an accurate and efficient low-bitwidth PTQ method designed for LLMs.
  arXiv  Detail & Related papers  (2023-10-12T05:25:49Z)

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.