lucidrains / memory-efficient-attention-pytorchLinks
Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
☆379Updated last year
Alternatives and similar repositories for memory-efficient-attention-pytorch
Users that are interested in memory-efficient-attention-pytorch are comparing it to the libraries listed below
Sorting:
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆214Updated 2 years ago
- An implementation of local windowed attention for language modeling☆460Updated 5 months ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆708Updated last week
- Memory Efficient Attention (O(sqrt(n)) for Jax and PyTorch☆184Updated 2 years ago
- Implementation of Linformer for Pytorch☆290Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆230Updated 10 months ago
- Sequence modeling with Mega.☆296Updated 2 years ago
- Implementation of Block Recurrent Transformer - Pytorch☆220Updated 10 months ago
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆204Updated last year
- ☆292Updated 6 months ago
- A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model☆595Updated 7 months ago
- Implementation of Flash Attention in Jax☆213Updated last year
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆784Updated last year
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆252Updated 2 years ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆214Updated 10 months ago
- Implementation of a Transformer, but completely in Triton☆270Updated 3 years ago
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆466Updated 2 years ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆345Updated last year
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆410Updated 6 months ago
- Code release for "Dropout Reduces Underfitting"☆313Updated 2 years ago
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores☆323Updated 6 months ago
- Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).☆225Updated 3 years ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆536Updated last year
- Root Mean Square Layer Normalization☆245Updated 2 years ago
- Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in P…☆204Updated last year
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆123Updated 11 months ago
- Annotated version of the Mamba paper☆486Updated last year
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆380Updated last year
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆366Updated last year
- Implementation of Bit Diffusion, Hinton's group's attempt at discrete denoising diffusion, in Pytorch☆350Updated last year