Skip to content
Change the repository type filter

All

    Repositories list

    • PostDiff

      Public
      [ICCV 2025] Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment
      Python
      0500Updated Feb 3, 2026Feb 3, 2026
    • LaCache

      Public
      [ICML 2025] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
      Python
      BSD 3-Clause "New" or "Revised" License
      21800Updated Nov 4, 2025Nov 4, 2025
    • LAMB

      Public
      Python
      0410Updated Aug 26, 2025Aug 26, 2025
    • [CVPR 2025] "Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training" by Lexington Whale…
      Python
      0300Updated Aug 24, 2025Aug 24, 2025
    • DiffCR

      Public
      Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
      Python
      Apache License 2.0
      21020Updated May 19, 2025May 19, 2025
    • LongMamba

      Public
      A training-free method for extending the context length of SSMs (State Space Models) and hybrid architectures.
      Python
      11210Updated Apr 26, 2025Apr 26, 2025
    • An open-sourced PyTorch library for developing energy efficient multiplication-less models and applications.
      Python
      Apache License 2.0
      01400Updated Feb 3, 2025Feb 3, 2025
    • [ECCV 2024 Oral] "Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields" by Yonggan Fu, Huaizhi Qu, Zhifan Ye, Chaojian Li, Ke…
      Python
      MIT License
      0810Updated Dec 14, 2024Dec 14, 2024
    • AmoebaLLM

      Public
      [NeurIPS 2024] "AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment" by Yonggan Fu, Zhongzhi Yu, Junwei Li, Jiayi Qian,…
      Python
      MIT License
      31900Updated Dec 13, 2024Dec 13, 2024
    • ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
      Python
      Apache License 2.0
      1811250Updated Oct 15, 2024Oct 15, 2024
    • Python
      MIT License
      115500Updated Oct 8, 2024Oct 8, 2024
    • LLM4HWDesign Starting Toolkit
      Python
      41910Updated Oct 4, 2024Oct 4, 2024
    • ACT

      Public
      [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
      Python
      14520Updated Jun 30, 2024Jun 30, 2024
    • Edge-LLM

      Public
      [DAC 2024] EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting
      Python
      108520Updated Jun 30, 2024Jun 30, 2024
    • [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
      Python
      Apache License 2.0
      33510Updated Jun 12, 2024Jun 12, 2024
    • [CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference
      Python
      Apache License 2.0
      13010Updated Mar 14, 2024Mar 14, 2024
    • NeRFool

      Public
      [ICML 2023] "NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations" by Yonggan Fu, Ye Yuan, Souvik Kun…
      Python
      MIT License
      11800Updated Mar 10, 2024Mar 10, 2024
    • CPT

      Public
      [ICLR 2021 Spotlight] "CPT: Efficient Deep Neural Network Training via Cyclic Precision" by Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, …
      Python
      MIT License
      63121Updated Mar 2, 2024Mar 2, 2024
    • [NeurIPS 2023] ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
      Python
      Apache License 2.0
      03010Updated Dec 6, 2023Dec 6, 2023
    • C
      0600Updated Oct 19, 2023Oct 19, 2023
    • BNS-GCN

      Public
      [MLSys 2022] "BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling" by Cheng Wan,…
      Python
      MIT License
      145600Updated Oct 6, 2023Oct 6, 2023
    • S3-Router

      Public
      [NeurIPS 2022] "Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing" by Yongg…
      Python
      MIT License
      21710Updated Sep 19, 2023Sep 19, 2023
    • ViTCoD

      Public
      [HPCA 2023] ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design
      Python
      Apache License 2.0
      1412930Updated Jun 27, 2023Jun 27, 2023
    • Hint-Aug

      Public
      Python
      MIT License
      0500Updated Jun 25, 2023Jun 25, 2023
    • [ICLR 2021] HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark
      Python
      MIT License
      2011720Updated Apr 18, 2023Apr 18, 2023
    • HALO

      Public
      The official code for [ECCV2020] "HALO: Hardware-aware Learning to Optimize"
      Python
      MIT License
      11000Updated Mar 22, 2023Mar 22, 2023
    • PipeGCN

      Public
      [ICLR 2022] "PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication" by Cheng Wan, Youjie Li, Cameron R. Wo…
      Python
      MIT License
      63400Updated Mar 15, 2023Mar 15, 2023
    • ViTALiTy

      Public
      ViTALiTy (HPCA'23) Code Repository
      Python
      Apache License 2.0
      72320Updated Mar 13, 2023Mar 13, 2023
    • Spline-EB

      Public
      [TMLR] Max-Affine Spline Insights Into Deep Network Pruning
      Python
      MIT License
      0100Updated Nov 12, 2022Nov 12, 2022
    • 71100Updated Oct 27, 2022Oct 27, 2022
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.