memory-efficient-attention-pytorch
performer-pytorch
Our great sponsors
| memory-efficient-attention-pytorch | performer-pytorch | |
|---|---|---|
| 2 | 2 | |
| 227 | 1,055 | |
| - | - | |
| 6.1 | 1.8 | |
| about 1 year ago | about 2 years ago | |
| Python | Python | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
memory-efficient-attention-pytorch
-
[Discussion] Fine tune model for long context
Check these efficient attention mechanism which are almost a drop in replacement: efficient attention flash attention
-
Will Transformers Take over Artificial Intelligence?
I would recommend Routing Transformer https://github.com/lucidrains/routing-transformer but the real truth is nothing beats full attention. Luckily, someone recently figured out how to get past the memory bottleneck. https://github.com/lucidrains/memory-efficient-attention-pyt...
performer-pytorch
-
[R] Rotary Positional Embeddings - a new relative positional embedding for Transformers that significantly improves convergence (20-30%) and works for both regular and efficient attention
Performer is the best linear attention variant, but linear attention is just one type of efficient attention solution. I have rotary embeddings already in the repo https://github.com/lucidrains/performer-pytorch and you can witness this phenomenon yourself by toggling it on / off
-
Why has Google's Performer model not replaced traditional softmax attention?
Here's an PyTorch implementation if you want to play around with it: lucidrains/performer-pytorch: An implementation of Performer, a linear attention-based transformer, in Pytorch (github.com)
What are some alternatives?
flash-attention - Fast and memory-efficient exact attention
long-range-arena - Long Range Arena for Benchmarking Efficient Transformers
x-transformers - A simple but complete full-attention transformer with a set of promising experimental features from various papers
Perceiver - Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow
memory-efficient-attention-pyt
reformer-pytorch - Reformer, the efficient Transformer, in Pytorch
vit-pytorch - Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
routing-transformer - Fully featured implementation of Routing Transformer
deep-implicit-attention - Implementation of deep implicit attention in PyTorch
Compact-Transformers - Escaping the Big Data Paradigm with Compact Transformers, 2021 (Train your Vision Transformers in 30 mins on CIFAR-10 with a single GPU!)
scenic - Scenic: A Jax Library for Computer Vision Research and Beyond