Skip to content

@compressionOrg compressionOrg

Change the repository type filter

All

    Repositories list

    95 repositories

    • admm-pruning

      Public
      Python
      •
      MIT License
      •2•0•0•0•Updated Apr 6, 2026Apr 6, 2026

    • Pruner-Zero

      Public
      [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs
      Python
      •
      MIT License
      •11•0•0•0•Updated Apr 6, 2026Apr 6, 2026

    • DSnoT

      Public
      Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
      Python
      •9•0•0•0•Updated Apr 5, 2026Apr 5, 2026

    • OwLore

      Public
      Official Pytorch Implementation of "OwLore: Outlier-weighed Layerwise Sampled Low-Rank Projection for Memory-Efficient LLM Fine-tuning" by Pengxiang Li, Lu Yin,…
      Python
      •7•0•0•0•Updated Apr 4, 2026Apr 4, 2026

    • SVD-LLM

      Public
      Official Code for "SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression"
      Python
      •
      Apache License 2.0
      •47•0•0•0•Updated Mar 29, 2026Mar 29, 2026

    • ASVD4LLM

      Public
      Activation-aware Singular Value Decomposition for Compressing Large Language Models
      Python
      •
      MIT License
      •16•0•0•0•Updated Mar 29, 2026Mar 29, 2026

    • EasyEdit

      Public
      [ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
      Jupyter Notebook
      •
      MIT License
      •372•0•0•0•Updated Jan 27, 2026Jan 27, 2026

    • CPSVD

      Public
      CPSVD: Enhancing Large Language Model Compression via Column-Preserving Singular Value Decomposition
      Python
      •
      Apache License 2.0
      •2•0•0•0•Updated Jan 6, 2026Jan 6, 2026

    • ARA

      Public
      Official code for ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression
      Python
      •
      Apache License 2.0
      •1•1•0•0•Updated Dec 28, 2025Dec 28, 2025

    • Dobi-SVD

      Public
      Official code implementation for 2025 ICLR accepted paper "Dobi-SVD : Differentiable SVD for LLM Compression and Some New Perspectives"
      Python
      •
      MIT License
      •9•0•0•0•Updated Dec 21, 2025Dec 21, 2025

    • adaptive-rank-selection-svd

      Public
      Implementation of Adaptive Rank Selections for Low-Rank Approximation of Language Models
      Python
      •2•0•0•0•Updated Dec 18, 2025Dec 18, 2025

    • EAGLE

      Public
      Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
      Python
      •
      Other
      •293•0•0•0•Updated Oct 13, 2025Oct 13, 2025

    • FiNE

      Public
      Code for "Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs" (ICLR 2025)
      Python
      •
      MIT License
      •3•0•0•0•Updated Oct 9, 2025Oct 9, 2025

    • FLAR-SVD

      Public
      [CVPRW25] 'FLAR-SVD: Latency-Aware SVD for (Vision) Model Compression' official reimplementation
      Python
      •
      Creative Commons Zero v1.0 Universal
      •2•0•0•0•Updated Oct 5, 2025Oct 5, 2025

    • FLAT-LLM

      Public
      Official code for FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression
      Python
      •
      MIT License
      •4•0•0•0•Updated Sep 11, 2025Sep 11, 2025

    • ReplaceMe

      Public
      Python
      •6•0•0•0•Updated Aug 22, 2025Aug 22, 2025

    • 2SSP

      Public
      2SSP: A Two-Stage Framework for Structured Pruning of LLMs
      Python
      •
      GNU General Public License v3.0
      •2•0•0•0•Updated Aug 18, 2025Aug 18, 2025

    • Selective_Context

      Public
      Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.
      Python
      •25•0•0•0•Updated Aug 12, 2025Aug 12, 2025

    • EntroDrop

      Public
      Python
      •
      Apache License 2.0
      •1•0•0•0•Updated Aug 2, 2025Aug 2, 2025

    • jemnlp

      Public
      Python
      •2•0•0•0•Updated Jul 26, 2025Jul 26, 2025

    • ShortGPT

      Public
      Unofficial implementations of block/layer-wise pruning methods for LLMs.
      Jupyter Notebook
      •
      MIT License
      •19•0•0•0•Updated Jul 15, 2025Jul 15, 2025

    • ImPart

      Public
      [ACL 2025] ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs
      Python
      •3•0•0•0•Updated Jul 14, 2025Jul 14, 2025

    • GRASP

      Public
      The official PyTorch implementation for "Rethinking Layer Removal: A Hybrid Pruning Framework Combining Layer Removal and Singular Value Selection for Efficient…
      Python
      •
      MIT License
      •1•0•0•0•Updated Jul 4, 2025Jul 4, 2025

    • Awesome-Efficient-LLM

      Public
      A curated list for Efficient Large Language Models
      Python
      •169•1•0•0•Updated Jun 23, 2025Jun 23, 2025

    • opencompass-0.2.3

      Public
      Apache License 2.0
      •0•0•0•0•Updated Jun 19, 2025Jun 19, 2025

    • opencompass

      Public
      OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets…
      Python
      •
      Apache License 2.0
      •819•0•0•0•Updated Jun 18, 2025Jun 18, 2025

    • LLM-Streamline

      Public
      Official implementation of the ICLR paper "Streamlining Redundant Layers to Compress Large Language Models"
      Python
      •4•0•0•0•Updated May 19, 2025May 19, 2025

    • slicegpt

      Public
      Python
      •
      MIT License
      •58•0•0•0•Updated May 7, 2025May 7, 2025

    • TransformerCompression

      Public
      For releasing code related to compression methods for transformers, accompanying our publications
      Python
      •
      MIT License
      •58•0•0•0•Updated May 5, 2025May 5, 2025

    • SLEB

      Public
      Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
      Python
      •
      MIT License
      •6•0•0•0•Updated May 4, 2025May 4, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.