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
• RobertCsordas / moeut
  ☆73Updated 7 months ago
• RobertCsordas / moe_layer
  sigma-MoE layer
  ☆18Updated last year
• kyleliang919 / Online-Subspace-Descent
  This repo is based on https://github.com/jiaweizzhao/GaLore
  ☆26Updated 6 months ago
• TRI-ML / linear_open_lm
  A repository for research on medium sized language models.
  ☆76Updated 9 months ago
• google-deepmind / asyncdiloco
  ☆43Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆42Updated 6 months ago
• RobertCsordas / moe_attention
  Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"
  ☆97Updated 5 months ago
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆45Updated 8 months ago
• frankxwang / dpo-prefix-sharing
  DPO, but faster 🚀
  ☆40Updated 3 months ago
• nanowell / Q-Sparse-LLM
  My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
  ☆31Updated 7 months ago
• VITA-Group / WeLore
  From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…
  ☆44Updated 8 months ago
• HazyResearch / prefix-linear-attention
  ☆52Updated 8 months ago
• berlino / seq_icl
  ☆51Updated 10 months ago
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated 9 months ago
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"
  ☆59Updated 5 months ago
• yidingjiang / ado
  The repository contains code for Adaptive Data Optimization
  ☆20Updated 3 months ago
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆26Updated 11 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
• eth-easl / fmengine
  Utilities for Training Very Large Models
  ☆58Updated 5 months ago
• wdlctc / mini-s
  ☆49Updated 4 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 last year
• facebookresearch / MemoryMosaics
  Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.
  ☆38Updated last month
• sustcsonglin / mamba-triton
  ☆47Updated last year
• evanatyourservice / llm-jax
  Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.
  ☆17Updated this week
• yikangshen / megablocks
  ☆18Updated 9 months ago
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆44Updated last year
• ethansmith2000 / TransformerExperiments
  ☆19Updated 5 months ago