arXiv:2608. 06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs.
LILA (Latent-Informed Layer Analysis) introduces a calibration‑free method for structured pruning of large language models by scoring neuron importance using the Kolmogorov–Smirnov distance between singular value distributions of full and neuron‑ablated feed‑forward network weight matrices. The approach requires no training, calibration data, or auxiliary networks, and outperforms existing methods such as PruneNet and SliceGPT on LLaMA‑2‑7B and Phi‑2 at various sparsity levels. After a single epoch of LoRA fine‑tuning, LILA matches heavily calibrated baselines, and a Neural Tangent Kernel analysis provides theoretical support for its spectral importance criterion. Additionally, LILA can dynamically allocate sparsity budgets, achieving state‑of‑the‑art generative preservation and revealing architectural bottlenecks at higher compression.
arXiv:2509. 14230v2 Announce Type: replace Abstract: While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance degradation and demand computationally retraining to recover capabilities.
Sparse autoencoders (SAEs) are commonly used to interpret large language models, but their reliability after pruning is unclear. This study shows that pruning’s effect on an SAE is governed by perturbation energy, a covariance-weighted norm, and that magnitude pruning distorts the representation space by ignoring activation geometry. Activation-aware pruning methods such as Wanda and SparseGPT better preserve SAE behavior, and the authors find that middle layers are especially vulnerable, leading them to propose a layer‑wise sparsity allocation that reduces perplexity for a given sparsity level.
COEC (Calibrated Orthogonal-Equivalence Compensation) is a training‑free framework that improves structured pruning of large language models by applying alternating left and right orthogonal rotations to the retained weight matrix. The method optimizes the right rotation on a reduced Stiefel manifold, rescales singular values via generalized cross‑validation, tempers the calibration Gram matrix, and adds an alignment penalty to preserve geometric relations between attention projections. Experiments on Llama‑3, Llama‑3.1, and Qwen2.5 show that COEC consistently improves perplexity and zero‑shot accuracy across multiple sparsity levels, outperforming existing compensation techniques.
arXiv:2603. 13418v2 Announce Type: replace Abstract: Structured pruning is widely applied to compress large language models (LLMs), but its performance depends heavily on how neuron importance is estimated.
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.
arXiv:2607. 22587v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance across diverse tasks but their deployment is constrained by the memory and compute cost of their parameters.
arXiv:2512.20636v2 Announce Type: replace-cross Abstract: Many self-attention sublayers in large language models (LLMs) can be removed with little to no loss. We attribute this to the Attention Suppr...
SparseDecoding is a decoding‑aware pruning framework that improves large language model inference by aligning pruning with the activations seen during actual autoregressive generation. It constructs calibration matrices from dense‑model activations (excluding prefill) and introduces an optimized N:M sparse matrix‑vector kernel with bitmask indexing to accelerate decoding. Experiments on models such as Llama‑3.1‑8B, Llama‑3.3‑70B, and Qwen3‑14B/32B show consistent performance gains over standard fixed‑text calibration and up to 1.48× wall‑clock speedup on A100 GPUs.
SHIFT-LLM is a training‑free post‑pruning correction framework that inserts a Linear Residual Adapter (LRA) at each depth‑pruned site in large language models. Each LRA preserves the original residual identity while adding a lightweight affine correction calibrated via closed‑form least‑squares regression on a small held‑out set, thereby approximating the hidden state that would have been produced by the removed block. Experiments across multiple model families and benchmarks show that SHIFT‑LLM consistently recovers accuracy lost to depth pruning, achieving gains up to +15.7 points on Llama‑3.1‑8B‑Instruct with only a few hundred calibration samples and no gradient computation.
arXiv:2605. 17289v2 Announce Type: replace-cross Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm.