Pith. sign in

REVIEW 5 cited by

LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.18356 v2 pith:HDIRBNKB submitted 2023-10-24 cs.CL cs.AIcs.LG

LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery

classification cs.CL cs.AIcs.LG
keywords lorashearknowledgellmspruningadaptorsdynamiceffectivelyefficient
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Language Models (LLMs) have transformed the landscape of artificial intelligence, while their enormous size presents significant challenges in terms of computational costs. We introduce LoRAShear, a novel efficient approach to structurally prune LLMs and recover knowledge. Given general LLMs, LoRAShear at first creates the dependency graphs over LoRA modules to discover minimally removal structures and analyze the knowledge distribution. It then proceeds progressive structured pruning on LoRA adaptors and enables inherent knowledge transfer to better preserve the information in the redundant structures. To recover the lost knowledge during pruning, LoRAShear meticulously studies and proposes a dynamic fine-tuning schemes with dynamic data adaptors to effectively narrow down the performance gap to the full models. Numerical results demonstrate that by only using one GPU within a couple of GPU days, LoRAShear effectively reduced footprint of LLMs by 20% with only 1.0% performance degradation and significantly outperforms state-of-the-arts. The source code will be available at https://github.com/microsoft/lorashear.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry

    cs.LG 2026-06 unverdicted novelty 6.0

    CascadeFormer tapers Transformer width with depth based on gradient fan-in asymmetry to match uniform baselines in perplexity while cutting latency 8.6%.

  2. Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation

    cs.LG 2025-09 conditional novelty 6.0

    PrunedLoRA tunes large-rank LoRA adapters and progressively structurally prunes A and B to a target low rank, empirically closing much of the LoRA-to-full-fine-tuning gap.

  3. MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs

    cs.LG 2025-06 unverdicted novelty 6.0

    MaskPro learns categorical distributions over groups of M weights to generate exact (N:M) sparsity via N-way sampling without replacement and stabilizes training with a moving average tracker of loss residuals.

  4. RAP: Runtime Adaptive Pruning for LLM Inference

    cs.LG 2025-05 unverdicted novelty 5.0

    RAP is a reinforcement learning framework for runtime-adaptive pruning of LLMs that jointly optimizes model weights and KV-cache usage under varying memory budgets.

  5. A Survey on Efficient Inference for Large Language Models

    cs.CL 2024-04 accept novelty 3.0

    The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.