lucidrains / mixture-of-expertsLinks
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
☆788Updated last year
Alternatives and similar repositories for mixture-of-experts
Users that are interested in mixture-of-experts are comparing it to the libraries listed below
Sorting:
- PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538☆1,149Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆352Updated last year
- ☆656Updated last month
- A curated reading list of research in Mixture-of-Experts(MoE).☆639Updated 9 months ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆793Updated last year
- A collection of AWESOME things about mixture-of-experts☆1,177Updated 7 months ago
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek/Kimi-K2/Qwen3 FP8/FP4☆870Updated this week
- A fast MoE impl for PyTorch☆1,769Updated 5 months ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆719Updated last week
- Code for the ALiBi method for transformer language models (ICLR 2022)☆538Updated last year
- Long Range Arena for Benchmarking Efficient Transformers☆762Updated last year
- Implementation of Linformer for Pytorch☆294Updated last year
- An implementation of local windowed attention for language modeling☆470Updated 3 weeks ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆309Updated 4 months ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆533Updated 2 months ago
- Rotary Transformer☆1,001Updated 3 years ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆477Updated last year
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆368Updated last year
- Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆1,239Updated last year
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.☆1,638Updated this week
- Large Context Attention☆719Updated 6 months ago
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆379Updated 2 years ago
- Pytorch library for fast transformer implementations☆1,725Updated 2 years ago
- [ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation☆820Updated 10 months ago
- Collection of papers on state-space models☆594Updated 3 months ago
- maximal update parametrization (µP)☆1,576Updated last year
- (Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from …☆173Updated last year
- ☆292Updated 7 months ago
- AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning (ICLR 2023).☆338Updated 2 years ago
- Helpful tools and examples for working with flex-attention☆908Updated 2 weeks ago