lucidrains / mixture-of-expertsLinks
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
☆815Updated 2 years ago
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☆1,188Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆363Updated last year
- ☆683Updated 2 months ago
- A curated reading list of research in Mixture-of-Experts(MoE).☆648Updated 11 months ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆801Updated last year
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆769Updated 2 months ago
- Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4☆934Updated 2 weeks ago
- A fast MoE impl for PyTorch☆1,806Updated 8 months ago
- A collection of AWESOME things about mixture-of-experts☆1,216Updated 10 months ago
- An implementation of local windowed attention for language modeling☆483Updated 3 months ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆544Updated last year
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆369Updated 2 years ago
- Implementation of Linformer for Pytorch☆299Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆331Updated 6 months ago
- Rotary Transformer☆1,039Updated 3 years ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆488Updated last year
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.☆1,656Updated this week
- Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆1,263Updated last year
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆383Updated 2 years ago
- Long Range Arena for Benchmarking Efficient Transformers☆765Updated last year
- AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning (ICLR 2023).☆353Updated 2 years ago
- ☆292Updated 10 months ago
- Pytorch library for fast transformer implementations☆1,745Updated 2 years ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆542Updated 5 months ago
- [ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters☆574Updated 8 months ago
- (Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from …☆181Updated last year
- [ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation☆866Updated last year
- Helpful tools and examples for working with flex-attention☆1,029Updated this week
- Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆423Updated last year
- Root Mean Square Layer Normalization☆256Updated 2 years ago