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
  ☆48Updated last year
• TRI-ML / linear_open_lm
  A repository for research on medium sized language models.
  ☆78Updated last year
• RobertCsordas / moe_attention
  Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"
  ☆102Updated last year
• RobertCsordas / moeut
  ☆89Updated last year
• RobertCsordas / moe_layer
  sigma-MoE layer
  ☆20Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆47Updated last year
• epfml / DenseFormer
  ☆82Updated last year
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆45Updated last year
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆45Updated 2 years 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 2 years ago
• 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 🚀
  ☆46Updated 11 months ago
• kaiokendev / cutoff-len-is-context-len
  Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit
  ☆63Updated 2 years ago
• McGill-NLP / length-generalization
  Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023
  ☆138Updated last year
• sustcsonglin / mamba-triton
  ☆50Updated last year
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …
  ☆60Updated last year
• google-deepmind / asyncdiloco
  ☆47Updated last year
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• HazyResearch / prefix-linear-attention
  ☆57Updated last year
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated last year
• kyegomez / Infini-attention
  Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…
  ☆57Updated last week
• r-three / RAD
  Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
  ☆45Updated 2 months ago
• berlino / seq_icl
  ☆53Updated last year
• lucidrains / PEER-pytorch
  Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind
  ☆131Updated last month
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆130Updated last year
• proger / hippogriff
  Griffin MQA + Hawk Linear RNN Hybrid
  ☆89Updated last year
• eth-easl / fmengine
  Utilities for Training Very Large Models
  ☆58Updated last year
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆55Updated last year
• kyegomez / Blockwise-Parallel-Transformer
  32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.
  ☆49Updated 2 years ago
• codekansas / rwkv
  RWKV model implementation
  ☆38Updated 2 years ago