Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional training.
arXiv:2606. 01544v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs.
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: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: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.
arXiv:2504.04342v2 Announce Type: replace Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly gro...
arXiv:2607. 17568v1 Announce Type: cross Abstract: Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups.
The paper introduces αp-LoRA, a rank-allocation strategy for low-rank adaptation (LoRA) in large language models that uses π-regularization (0 < p < 1) to induce sparsity in rank-one components. By regularizing the energy of each component, redundant parts are encouraged to vanish while important ones are retained, and the authors derive a proximal subproblem that reduces the matrix optimization to a two‑dimensional thresholding criterion. Experiments on natural language understanding and question‑answering tasks show that αp-LoRA achieves performance competitive with existing LoRA baselines.
arXiv:2606.21847v2 Announce Type: replace-cross Abstract: Low-rank decomposition is a promising compression paradigm for large language models (LLMs), yet its effectiveness hinges on rank budget allo...
With the rapid development of large-scale pre-trained language models based on Transformer architectures, their high computational and memory costs have become a major obstacle to deployment, especial...
The paper introduces REP‑LIE, a resource‑efficient pruning method for Transformer models that estimates weight importance using gradients from LoRA low‑rank matrices, avoiding full gradient computation. It incorporates a stability score to iteratively prune unimportant parameters and then fine‑tunes the pruned model with lightweight updates, eliminating the need for full‑parameter optimization. Experiments on medium‑scale encoders and large‑scale generative models such as LLaMA‑7B and Mistral‑7B show that REP‑LIE achieves competitive performance compared to existing pruning approaches.
arXiv:2510. 00192v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational capacity often lags behind full fine-tuning.
arXiv:2609.22131v1 Announce Type: cross Abstract: Structured pruning is a promising approach for reducing the substantial inference costs of Large Language Models (LLMs) while maintaining hardware ef...