low-rank 开源项目推荐（73 个）

microsoft /LoRA

这是用于Loralib的代码，Loralib是“LoRA：大型语言模型的低秩自适应”技术的实现方式。

lezcano /geotorch

Constrained optimization toolkit for PyTorch

ByteDance-Seed /ShadowKV

[ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

VITA-Group /Q-GaLore

Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.

gudaochangsheng /WaDi

[CVPR 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis

liuyang12 /DeSCI

Rank Minimization for Snapshot Compressive Imaging (TPAMI'19)

juliagusak /model-compression-and-acceleration-progress

Repository to track the progress in model compression and acceleration

musco-ai /musco-pytorch

MUSCO: MUlti-Stage COmpression of neural networks

abdelfattah-lab /xKV

xKV: Cross-Layer SVD for KV-Cache Compression [ICML 2026]

Reason-Wang /flan-alpaca-lora

本仓库包含用羊驼指令和低等级适应训练Flan t5的代码。

NVlabs /EoRA

[ICLRW'26] EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation

YyzHarry /SV-RL

[ICLR 2020, Oral] Harnessing Structures for Value-Based Planning and Reinforcement Learning

mtntruong /LRT-HDR

Python code and data for "Deep Unrolled Low-Rank Tensor Completion for High Dynamic Range Imaging", IEEE TIP 2022

Chunjiang-Intelligence /low-rank-decay

「Low-Rank Decay」的官方实现。

thkimKETI /CNN_compression_rank_selection_BayesOpt

Bayesian Optimization-Based Global Optimal Rank Selection for Compression of Convolutional Neural Networks, IEEE Access

mtntruong /AGTC

Python code and data for "Attention-Guided Low-Rank Tensor Completion", IEEE TPAMI 2024

lim142857 /Sparsifiner

Demo code for CVPR2023 paper "Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers"

iamhankai /voiceMusicSeparation

Voice Music Separation competing for 6th Huawei Cup in ZJU

YangLabHKUST /mfair

mfair: Matrix Factorization with Auxiliary Information in R

DEVANSH-DVJ /Video-denoising

Video Denoising using Low Rank Matrix completion