idiap / fast-transformersLinks
Pytorch library for fast transformer implementations
☆1,727Updated 2 years ago
Alternatives and similar repositories for fast-transformers
Users that are interested in fast-transformers are comparing it to the libraries listed below
Sorting:
- An implementation of Performer, a linear attention-based transformer, in Pytorch☆1,144Updated 3 years ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆794Updated last year
- Reformer, the efficient Transformer, in Pytorch☆2,180Updated 2 years ago
- Long Range Arena for Benchmarking Efficient Transformers☆762Updated last year
- Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch☆1,165Updated 2 years ago
- My take on a practical implementation of Linformer for Pytorch.☆417Updated 3 years ago
- Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"☆1,584Updated 5 years ago
- An All-MLP solution for Vision, from Google AI☆1,036Updated last month
- Longformer: The Long-Document Transformer☆2,159Updated 2 years ago
- An implementation of local windowed attention for language modeling☆472Updated last month
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆736Updated 3 weeks ago
- PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538☆1,157Updated last year
- PyTorch implementation of some attentions for Deep Learning Researchers.☆534Updated 3 years ago
- Profiling and inspecting memory in pytorch☆1,064Updated last year
- PyTorch extensions for high performance and large scale training.☆3,361Updated 3 months ago
- Implementation of Linformer for Pytorch☆295Updated last year
- Fast, differentiable sorting and ranking in PyTorch☆827Updated 2 months ago
- torch-optimizer -- collection of optimizers for Pytorch☆3,135Updated last year
- Structured state space sequence models☆2,706Updated last year
- Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute☆1,532Updated 4 years ago
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆792Updated last year
- Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"☆1,064Updated last year
- Pytorch Lightning code guideline for conferences☆1,279Updated last year
- Standalone TFRecord reader/writer with PyTorch data loaders☆889Updated 3 months ago
- A fast MoE impl for PyTorch☆1,777Updated 6 months ago
- higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual tr…☆1,621Updated 3 years ago
- Fully featured implementation of Routing Transformer☆297Updated 3 years ago
- Source code for "On the Relationship between Self-Attention and Convolutional Layers"☆1,109Updated 2 years ago
- DeLighT: Very Deep and Light-Weight Transformers☆469Updated 4 years ago
- [ICLR 2020] Lite Transformer with Long-Short Range Attention☆612Updated last year