Alternatives and similar repositories for MoSA

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

• 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…
  ☆56Updated 2 years ago
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆56Updated last year
• chuanyang-Zheng / DAPE
  The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"
  ☆41Updated last year
• abdelfattah-lab / TokenButler
  ☆27Updated 2 months ago
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆62Updated last year
• Doraemonzzz / xmixers
  Xmixers: A collection of SOTA efficient token/channel mixers
  ☆28Updated 5 months ago
• GATECH-EIC / Linearized-LLM
  [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
  ☆35Updated last year
• kyegomez / MultiQueryAttention
  This is a simple torch implementation of the high performance Multi-Query Attention
  ☆16Updated 2 years ago
• nasosger / MuToR
  [NeurIPS '25] Multi-Token Prediction Needs Registers
  ☆26Updated last month
• RobertCsordas / moeut
  ☆91Updated last year
• TianjinYellow / SPAM-Optimizer
  ☆36Updated 11 months ago
• howard-hou / RWKV-X
  RWKV-X is a Linear Complexity Hybrid Language Model based on the RWKV architecture, integrating Sparse Attention to improve the model's l…
  ☆54Updated last month
• IST-DASLab / RoSA
  Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)
  ☆44Updated last year
• OpenNLPLab / HGRN
  [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…
  ☆66Updated last year
• kamanphoebe / Look-into-MoEs
  [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models
  ☆60Updated last year
• NJUNLP / MoE-LPR
  ☆21Updated last year
• fla-org / flash-bidirectional-linear-attention
  Triton implement of bi-directional (non-causal) linear attention
  ☆65Updated last week
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆89Updated last year
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆27Updated last year
• frankxwang / dpo-prefix-sharing
  DPO, but faster 🚀
  ☆47Updated last year
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆47Updated last year
• wang-kee / LiNeS
  Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"
  ☆32Updated last year
• assafbk / DeciMamba
  DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)
  ☆32Updated 10 months ago
• zhixuan-lin / forgetting-transformer
  [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning
  ☆137Updated last month
• sail-sg / SkyLadder
  The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
  ☆42Updated last month
• chijames / KERPLE
  ☆20Updated 3 years ago
• Infini-AI-Lab / S2FT
  ☆19Updated last year
• sjelassi / transformers_ssm_copy
  ☆35Updated last year
• OpenMOSS / LongLLaDA
  [AAAI26] LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs
  ☆52Updated 2 months ago
• kyegomez / Blockwise-Parallel-Transformer
  32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.
  ☆50Updated 2 years ago