lucidrains / FLASH-pytorch
Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"
☆360Updated last year
Alternatives and similar repositories for FLASH-pytorch:
Users that are interested in FLASH-pytorch are comparing it to the libraries listed below
- [ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention☆188Updated 2 years ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆751Updated 10 months ago
- An implementation of local windowed attention for language modeling☆429Updated 2 months ago
- Implementation of Linformer for Pytorch☆274Updated last year
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 2 years ago
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆714Updated last year
- Sequence modeling with Mega.☆295Updated 2 years ago
- ☆875Updated 10 months ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆518Updated last year
- Rotary Transformer☆916Updated 3 years ago
- The pure and clear PyTorch Distributed Training Framework.☆276Updated last year
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆651Updated 3 months ago
- My take on a practical implementation of Linformer for Pytorch.☆413Updated 2 years ago
- An implementation of Performer, a linear attention-based transformer, in Pytorch☆1,116Updated 3 years ago
- ☆189Updated last year
- Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models☆781Updated 8 months ago
- Implement the paper "Self-Attention with Relative Position Representations"☆127Updated 4 years ago
- PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538☆1,079Updated 11 months ago
- Fully featured implementation of Routing Transformer☆289Updated 3 years ago
- Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms☆259Updated 3 years ago
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆372Updated last year
- Implementation of "Attention Is Off By One" by Evan Miller☆190Updated last year
- A pytorch &keras implementation and demo of Fastformer.☆187Updated 2 years ago
- RoFormer V1 & V2 pytorch☆490Updated 2 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆211Updated 2 years ago
- About Code release for "Flowformer: Linearizing Transformers with Conservation Flows" (ICML 2022), https://arxiv.org/pdf/2202.06258.pdf☆315Updated 8 months ago
- (Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from …☆158Updated 10 months ago
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆260Updated 3 years ago
- [ICLR 2024]EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling(https://arxiv.org/abs/2310.04691)☆119Updated last year
- An implementation of the efficient attention module.☆305Updated 4 years ago