Alternatives and similar repositories for moe:

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

• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆47Updated last year
• sustcsonglin / mamba-triton
  ☆47Updated last year
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆27Updated last year
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆45Updated 9 months ago
• RobertCsordas / moe_attention
  Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"
  ☆97Updated 7 months ago
• lucidrains / pause-transformer
  Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…
  ☆53Updated last year
• RobertCsordas / moeut
  ☆78Updated 8 months ago
• HazyResearch / prefix-linear-attention
  ☆53Updated 9 months ago
• TRI-ML / linear_open_lm
  A repository for research on medium sized language models.
  ☆76Updated 11 months ago
• google-deepmind / asyncdiloco
  ☆43Updated last year
• kyleliang919 / Online-Subspace-Descent
  This repo is based on https://github.com/jiaweizzhao/GaLore
  ☆27Updated 7 months ago
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆43Updated 7 months ago
• RobertCsordas / moe_layer
  sigma-MoE layer
  ☆18Updated last year
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆45Updated last year
• berlino / seq_icl
  ☆51Updated 11 months ago
• yikangshen / megablocks
  ☆20Updated 11 months ago
• tobiaskatsch / GatedLinearRNN
  ☆27Updated last year
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆60Updated last year
• prateeky2806 / ComPEFT
  ☆25Updated last year
• glassroom / heinsen_attention
  Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)
  ☆24Updated 10 months ago
• Infini-AI-Lab / gsm_infinite
  ☆44Updated 2 months ago
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆54Updated 8 months ago
• kyegomez / Blockwise-Parallel-Transformer
  32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.
  ☆48Updated last year
• Zyphra / Zyda_processing
  ☆33Updated 10 months ago
• sustcsonglin / gated_linear_attention_layer
  ☆32Updated last year
• wdlctc / mini-s
  ☆50Updated 6 months ago
• nanowell / Q-Sparse-LLM
  My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
  ☆32Updated 8 months ago
• renll / SeqBoat
  [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling
  ☆36Updated last year
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆30Updated 10 months ago
• evanatyourservice / llm-jax
  Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.
  ☆17Updated last month