Alternatives and similar repositories for switchhead

Users that are interested in switchhead are comparing it to the libraries listed below

• chuanyang-Zheng / DAPE
  The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"
  ☆39Updated last year
• GATECH-EIC / Linearized-LLM
  [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
  ☆35Updated last year
• WailordHe / DenseSSM
  A repository for DenseSSMs
  ☆88Updated last year
• TianjinYellow / SPAM-Optimizer
  ☆34Updated 6 months ago
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆54Updated last year
• kyegomez / Mixture-of-Depths
  Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆106Updated this week
• fla-org / flash-bidirectional-linear-attention
  Triton implement of bi-directional (non-causal) linear attention
  ☆56Updated 8 months ago
• MikaStars39 / StableMask
  PyTorch implementation of StableMask (ICML'24)
  ☆14Updated last year
• sramshetty / mixture-of-depths
  An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆36Updated last year
• AkideLiu / MiniCache
  ☆10Updated last year
• deep-spin / adasplash
  AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)
  ☆26Updated last week
• abdelfattah-lab / TokenButler
  ☆25Updated 2 months ago
• htqin / IR-QLoRA
  [ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retenti…
  ☆67Updated last year
• zhixuan-lin / forgetting-transformer
  [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning
  ☆131Updated 2 weeks ago
• krafton-ai / mambaformer-icl
  MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248
  ☆57Updated last year
• VITA-Group / Random-MoE-as-Dropout
  [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…
  ☆55Updated 2 years ago
• thunlp / SparsingLaw
  The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".
  ☆26Updated 11 months ago
• qiuzh20 / gated_attention
  The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…
  ☆83Updated 3 weeks ago
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆43Updated last year
• BaiTheBest / SparseLLM
  Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)
  ☆66Updated 6 months ago
• RobertCsordas / moe_attention
  Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"
  ☆99Updated last year
• nasosger / MuToR
  [NeurIPS '25] Multi-Token Prediction Needs Registers
  ☆20Updated last month
• IST-DASLab / RoSA
  Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)
  ☆44Updated last year
• VILA-Lab / GBLM-Pruner
  Are gradient information useful for pruning of LLMs?
  ☆46Updated last month
• shaochenze / PatchTrain
  Code for paper "Patch-Level Training for Large Language Models"
  ☆88Updated 10 months ago
• pprp / Pruner-Zero
  [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs
  ☆94Updated 10 months ago
• piotrpiekos / MoSA
  User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…
  ☆25Updated 5 months ago
• jiwonsong-dev / ReasoningPathCompression
  Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"
  ☆22Updated 4 months ago
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆61Updated last year
• ylsung / rsq
  Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"
  ☆19Updated 4 months ago