Alternatives and similar repositories for memory-efficient-attention

Users that are interested in memory-efficient-attention are comparing it to the libraries listed below

• lucidrains / flash-cosine-sim-attention
  Implementation of fused cosine similarity attention in the same style as Flash Attention
  ☆214Updated 2 years ago
• facebookresearch / diffq
  DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight …
  ☆236Updated 2 years ago
• lucidrains / Mega-pytorch
  Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena
  ☆204Updated last year
• lucidrains / Adan-pytorch
  Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch
  ☆252Updated 2 years ago
• HomebrewML / revlib
  Simple and efficient RevNet-Library for PyTorch with XLA and DeepSpeed support and parameter offload
  ☆128Updated 2 years ago
• lucidrains / memory-efficient-attention-pytorch
  Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
  ☆379Updated 2 years ago
• lucidrains / triton-transformer
  Implementation of a Transformer, but completely in Triton
  ☆273Updated 3 years ago
• lucidrains / fast-transformer-pytorch
  Implementation of Fast Transformer in Pytorch
  ☆175Updated 3 years ago
• lucidrains / flash-attention-jax
  Implementation of Flash Attention in Jax
  ☆215Updated last year
• lucidrains / PaLM-jax
  Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)
  ☆187Updated 3 years ago
• facebookresearch / mega
  Sequence modeling with Mega.
  ☆296Updated 2 years ago
• lucidrains / nystrom-attention
  Implementation of Nyström Self-attention, from the paper Nyströmformer
  ☆137Updated 4 months ago
• jiaweizzhao / ZerO-initialization
  ☆74Updated 2 years ago
• lucidrains / panoptic-transformer
  Another attempt at a long-context / efficient transformer by me
  ☆38Updated 3 years ago
• HomebrewML / HomebrewNLP-torch
  A case study of efficient training of large language models using commodity hardware.
  ☆68Updated 3 years ago
• lucidrains / hourglass-transformer-pytorch
  Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI
  ☆91Updated 3 years ago
• OATML / RHO-Loss
  ☆208Updated 2 years ago
• NVIDIA / transformer-ls
  Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).
  ☆225Updated 3 years ago
• lucidrains / axial-positional-embedding
  Axial Positional Embedding for Pytorch
  ☆83Updated 5 months ago
• google-research / diffstride
  TF/Keras code for DiffStride, a pooling layer with learnable strides.
  ☆124Updated 3 years ago
• lucidrains / mlp-gpt-jax
  A GPT, made only of MLPs, in Jax
  ☆58Updated 4 years ago
• ctlllll / SGConv
  ☆163Updated 2 years ago
• tmbdev-archive / webdataset-lightning
  A small demonstration of using WebDataset with ImageNet and PyTorch Lightning
  ☆74Updated last year
• facebookresearch / torchdim
  Named tensors with first-class dimensions for PyTorch
  ☆332Updated 2 years ago
• lucidrains / CoLT5-attention
  Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch
  ☆228Updated 10 months ago
• lucidrains / ponder-transformer
  Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper
  ☆81Updated 3 years ago
• rwightman / efficientnet-jax
  EfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax
  ☆128Updated last year
• lucidrains / long-short-transformer
  Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch
  ☆119Updated 4 years ago
• mlpen / Nystromformer
  ☆378Updated last year
• lucidrains / feedback-transformer-pytorch
  Implementation of Feedback Transformer in Pytorch
  ☆107Updated 4 years ago