Alternatives and similar repositories for soft-moe-pytorch

Users that are interested in soft-moe-pytorch are comparing it to the libraries listed below

• lucidrains / st-moe-pytorch
  Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch
  ☆375Updated last year
• OscarXZQ / weight-selection
  ☆191Updated last year
• bfshi / TOAST
  Official code for "TOAST: Transfer Learning via Attention Steering"
  ☆188Updated 2 years ago
• AmeenAli / HiddenMambaAttn
  Official PyTorch Implementation of "The Hidden Attention of Mamba Models"
  ☆232Updated 2 months ago
• gstoica27 / ZipIt
  A framework for merging models solving different tasks with different initializations into one multi-task model without any additional tr…
  ☆309Updated last year
• lucidrains / infini-transformer-pytorch
  Implementation of Infini-Transformer in Pytorch
  ☆112Updated last year
• jzhang38 / LongMamba
  Some preliminary explorations of Mamba's context scaling.
  ☆218Updated last year
• apple / ml-sigmoid-attention
  ☆304Updated 8 months ago
• jxiw / MambaInLlama
  [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models
  ☆234Updated 2 months ago
• bobby-he / simplified_transformers
  ☆293Updated last year
• test-time-training / ttt-lm-jax
  Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States
  ☆445Updated 2 months ago
• kyegomez / Mixture-of-Depths
  Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆111Updated last month
• transformer-vq / transformer_vq
  ☆200Updated 2 years ago
• goombalab / hydra
  Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"
  ☆170Updated 11 months ago
• lucidrains / recurrent-memory-transformer-pytorch
  Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch
  ☆421Updated last year
• fkodom / soft-mixture-of-experts
  PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)
  ☆81Updated 2 years ago
• fkodom / yet-another-retnet
  A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…
  ☆106Updated 2 years ago
• DAMO-NLP-SG / Inf-CLIP
  [CVPR 2025 Highlight] The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for C…
  ☆275Updated 11 months ago
• lucidrains / multimodal-dit-pytorch
  Implementation of a multimodal diffusion transformer in Pytorch
  ☆107Updated last year
• pengzhangzhi / Awesome-Mamba
  Awesome list of papers that extend Mamba to various applications.
  ☆139Updated 7 months ago
• lucidrains / mixture-of-attention
  Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts
  ☆121Updated last year
• bwconrad / soft-moe
  PyTorch implementation of "From Sparse to Soft Mixtures of Experts"
  ☆67Updated 2 years ago
• haoliuhl / language-quantized-autoencoders
  Language Quantized AutoEncoders
  ☆111Updated 2 years ago
• Haiyang-W / TokenFormer
  [ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
  ☆581Updated 11 months ago
• berlino / gated_linear_attention
  ☆106Updated last year
• zhixuan-lin / forgetting-transformer
  [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning
  ☆134Updated 3 weeks ago
• bfshi / scaling_on_scales
  When do we not need larger vision models?
  ☆413Updated 11 months ago
• Arnav0400 / ViT-Slim
  Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”
  ☆251Updated 4 months ago
• goombalab / phi-mamba
  Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…
  ☆118Updated last year
• lucidrains / titok-pytorch
  Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"
  ☆183Updated last year