Pytorch library for fast transformer implementations
☆1,785Mar 23, 2023Updated 3 years ago
Alternatives and similar repositories for fast-transformers
Users that are interested in fast-transformers are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An implementation of Performer, a linear attention-based transformer, in Pytorch☆1,183Feb 2, 2022Updated 4 years ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆845May 5, 2024Updated 2 years ago
- Reformer, the efficient Transformer, in Pytorch☆2,193Jun 21, 2023Updated 3 years ago
- My take on a practical implementation of Linformer for Pytorch.☆425Jul 27, 2022Updated 4 years ago
- Long Range Arena for Benchmarking Efficient Transformers☆787Dec 16, 2023Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Fully featured implementation of Routing Transformer☆300Nov 6, 2021Updated 5 years ago
- Understanding the Difficulty of Training Transformers☆332May 31, 2022Updated 4 years ago
- ☆3,718Sep 21, 2022Updated 4 years ago
- A concise but complete full-attention transformer with a set of promising experimental features from various papers☆5,964Updated this week
- Longformer: The Long-Document Transformer☆2,209Feb 8, 2023Updated 3 years ago
- PyTorch extensions for high performance and large scale training.☆3,404Apr 26, 2025Updated last year
- DeLighT: Very Deep and Light-Weight Transformers☆469Oct 16, 2020Updated 6 years ago
- [ICLR 2020] Lite Transformer with Long-Short Range Attention☆609Jul 11, 2024Updated 2 years ago
- list of efficient attention modules☆1,028Aug 23, 2021Updated 5 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆390Oct 18, 2023Updated 3 years ago
- Fast Block Sparse Matrices for Pytorch☆551Jan 21, 2021Updated 5 years ago
- Transformer training code for sequential tasks☆610Sep 14, 2021Updated 5 years ago
- Hopfield Networks is All You Need☆1,978Apr 23, 2023Updated 3 years ago
- FastFormers - highly efficient transformer models for NLU☆702Mar 21, 2025Updated last year
- Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)☆9,638Aug 26, 2026Updated 2 months ago
- Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute☆1,530Nov 18, 2020Updated 6 years ago
- Fast, general, and tested differentiable structured prediction in PyTorch☆1,134Apr 20, 2022Updated 4 years ago
- Transformer related optimization, including BERT, GPT☆6,460Mar 27, 2024Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Structured state space sequence models☆2,933Jul 17, 2024Updated 2 years ago
- Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"☆1,613Aug 12, 2020Updated 6 years ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,582Updated this week
- Facebook AI Research Sequence-to-Sequence Toolkit written in Python.☆32,205Sep 30, 2025Updated last year
- An implementation of the efficient attention module.☆332Nov 30, 2020Updated 5 years ago
- Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)☆2,110Jan 4, 2022Updated 4 years ago
- PyTorch original implementation of Cross-lingual Language Model Pretraining.☆2,921Feb 14, 2023Updated 3 years ago
- [NeurIPS 2020] Official Implementation: "SMYRF: Efficient Attention using Asymmetric Clustering".☆50Sep 6, 2023Updated 3 years ago
- ☆221Jun 8, 2020Updated 6 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention☆272Aug 10, 2021Updated 5 years ago
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch☆9,007Nov 9, 2026Updated last week
- Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch☆1,224Oct 26, 2026Updated 3 weeks ago
- torch-optimizer -- collection of optimizers for Pytorch☆3,172Mar 22, 2024Updated 2 years ago
- [NeurIPS 2021 Spotlight] & [IJCV 2024] SOFT: Softmax-free Transformer with Linear Complexity☆311Oct 24, 2026Updated 3 weeks ago
- Single Headed Attention RNN - "Stop thinking with your head"☆1,181Nov 27, 2021Updated 4 years ago
- Implementation of Fast Transformer in Pytorch☆176Aug 26, 2021Updated 5 years ago
Are these results useful?