Alternatives and similar repositories for dynamic-sparsity

Users that are interested in dynamic-sparsity are comparing it to the libraries listed below

• abdelfattah-lab / shadow_llm
  ☆10Updated last year
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆84Updated last month
• SeoLabCornell / torch2chip
  Torch2Chip (MLSys, 2024)
  ☆54Updated 6 months ago
• PingchengDong / GQA-LUT
  The official implementation of the DAC 2024 paper GQA-LUT
  ☆20Updated 9 months ago
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆59Updated 6 months ago
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆48Updated 2 months ago
• spcl / sten
  Sparsity support for PyTorch
  ☆37Updated 6 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆98Updated 3 months ago
• north-numerical-computing / tensor-cores-numerical-behavior
  Test suite for probing the numerical behavior of NVIDIA tensor cores
  ☆41Updated last year
• abdelfattah-lab / nitro
  Lightweight Python Wrapper for OpenVINO, enabling LLM inference on NPUs
  ☆23Updated 10 months ago
• sIncerass / QBERT
  ☆15Updated 2 years ago
• cornell-zhang / llm-datatypes
  Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
  ☆27Updated last year
• apuaaChen / EVT_AE
  Artifacts of EVT ASPLOS'24
  ☆26Updated last year
• maestro-project / frame
  FRAME: Fast Roofline Analytical Modeling and Estimation
  ☆38Updated 2 years ago
• sfox14 / block_minifloat
  Training with Block Minifloat number representation
  ☆16Updated 4 years ago
• spcl / substation
  Research and development for optimizing transformers
  ☆131Updated 4 years ago
• exists-forall / striped_attention
  ☆41Updated last year
• VITA-Group / Q-Hitter
  ☆15Updated last year
• casys-kaist / EnvPipe
  ☆25Updated 2 years ago
• SNU-ARC / any-precision-llm
  [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
  ☆116Updated 3 months ago
• anony-sub / chameleon
  Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
  ☆27Updated 5 years ago
• microsoft / SparTA
  ☆152Updated last year
• SqueezeAILab / SqueezedAttention
  [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference
  ☆54Updated 10 months ago
• brightlaboratory / polydl
  ☆11Updated 4 years ago
• Jokeren / triton-samples
  ☆28Updated 9 months ago
• awslabs / ratex
  ☆23Updated last month
• HanGuo97 / hilt
  ☆33Updated last week
• pku-liang / ArkVale
  ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)
  ☆43Updated 10 months ago
• mit-han-lab / spatten
  [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
  ☆107Updated last year
• hao-ai-lab / MuxServe
  ☆72Updated last year