Weight-Redundancy Pruning (WRP), a forward-free depth-pruning method that estimates inter-layer redundancy from checkpoint weights to select blocks without calibration data or model forward passes, consistently outperforms existing forward-free magnitude pruning and approaches the performance of activation-based methods.
Abstract
Depth pruning reduces large language model (LLM) inference cost by removing complete Transformer blocks. Activation-based methods collect hidden states through forward passes on calibration data, while existing forward-free methods score each Transformer block separately without measuring similarity between blocks. We propose Weight-Redundancy Pruning (WRP), a forward-free depth-pruning method that estimates inter-layer redundancy from checkpoint weights to select blocks without calibration data or model forward passes. WRP compares attention output and MLP down-projection weights across layers and combines their pairwise similarities with relative projection-scale information. The resulting all-pairs similarity matrix guides layer grouping and block selection. Across multiple pruning settings, model families, and downstream tasks, WRP consistently outperforms existing forward-free magnitude pruning and approaches the performance of activation-based methods.
Structured pruning reduces LLM inference costs by removing model components to produce smaller dense models. However, existing methods can cause reasoning performance to collapse on long-form reasoning tasks such as AIME. We propose \textit{LayerTrim}, a training-free structured pruning method that identifies redundant...
Woo-Sang Lim, Haneul Yoo, Vincent-Daniel Yun et al.· 1 citation
As large language models (LLMs) grow more powerful, their scale makes them costly to serve. Depth pruning offers a practical route to efficiency by directly reducing memory and latency without hardware-specific support. However, we observe that transformer layers exhibit markedly different task-dependent layer contribu...
Guan-Chen Li, Yi-Xing Xu, Xuan-Wu Yin et al.· 0 citations
Training-free pruning removes weights from pretrained large language models to reduce their deployment cost. However, existing approaches typically consider only the total number of retained weights. Consequently, their pruning decisions do not account for how target hardware stores and processes those weights. These m...
C. Barker, A. Paraskeva, J. V. van Rijn et al.· 0 citations
Looped transformers reuse the same layer multiple times, allowing inference compute to be adjusted without changing the model. Recent adaptive-depth methods train the model across multiple loop depths from the beginning of training. We introduce fixed-first training, which varies model depth only during a short final p...
Andrei Piterbarg, Sean McLeish, Dhruv B. Pai et al.· 0 citations
This work characterize the effect of a residual-stream perturbation through both its activation covariance and the local sensitivity of the model output, and derives a tractable spectral upper bound that reduces subspace selection to an eigendecomposition of a sensitivity-weighted covariance matrix, retaining the effic...
Chayne Thrash, Ke Chen, Soheil Kolouri· arXiv.org· 0 citations
The Global State Model (GSM), a causal encoder--decoder architecture that concentrates the selection and aggregation of long-range information in the encoding stage, is introduced, offering a shared-state architecture for efficient language modeling.
Yun Zheng, Bin Wen, Xiao-Jie Wang et al.· arXiv.org· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.