Alternatives and similar repositories for pytorch-custom-mma

Users that are interested in pytorch-custom-mma are comparing it to the libraries listed below

• lucidrains / token-shift-gpt
  Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing
  ☆50Updated 3 years ago
• lucidrains / autoregressive-linear-attention-cuda
  CUDA implementation of autoregressive linear attention, with all the latest research findings
  ☆44Updated 2 years ago
• lucidrains / einops-exts
  Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️
  ☆54Updated 2 years ago
• srush / mamba-scans
  Blog post
  ☆17Updated last year
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated last year
• lucidrains / panoptic-transformer
  Another attempt at a long-context / efficient transformer by me
  ☆38Updated 3 years ago
• lucidrains / memory-editable-transformer
  My explorations into editing the knowledge and memories of an attention network
  ☆35Updated 2 years ago
• lucidrains / holodeck-pytorch
  Implementation of a holodeck, written in Pytorch
  ☆18Updated last year
• lucidrains / rela-transformer
  Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012
  ☆49Updated 3 years ago
• glassroom / heinsen_attention
  Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)
  ☆24Updated last year
• rwightman / imagenet-12k
  ImageNet-12k subset of ImageNet-21k (fall11)
  ☆21Updated 2 years ago
• yikangshen / megablocks
  ☆20Updated last year
• eth-easl / fmengine
  Utilities for Training Very Large Models
  ☆58Updated 8 months ago
• sayakpaul / big_vision_experiments
  Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.
  ☆22Updated 2 years ago
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆43Updated 9 months ago
• sustcsonglin / gated_linear_attention_layer
  ☆32Updated last year
• kyegomez / Blockwise-Parallel-Transformer
  32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.
  ☆48Updated 2 years ago
• srush / tangent
  Source-to-Source Debuggable Derivatives in Pure Python
  ☆15Updated last year
• gregorbachmann / scaling_mlps
  ☆51Updated last year
• lucidrains / mlp-gpt-jax
  A GPT, made only of MLPs, in Jax
  ☆58Updated 4 years ago
• lucidrains / esbn-transformer
  An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols
  ☆16Updated 3 years ago
• RobertCsordas / linear_layer_as_attention
  The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …
  ☆16Updated last week
• lucidrains / kronecker-attention-pytorch
  Implementation of Kronecker Attention in Pytorch
  ☆19Updated 4 years ago
• RobertCsordas / moe
  Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
  ☆38Updated last week
• renll / SeqBoat
  [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling
  ☆37Updated last year
• LAION-AI / laion50BU
  Un-*** 50 billions multimodality dataset
  ☆23Updated 2 years ago
• AranKomat / Metroplex
  ☆21Updated 2 years ago
• ronghanghu / vit_10b_fsdp_example
  See details in https://github.com/pytorch/xla/blob/r1.12/torch_xla/distributed/fsdp/README.md
  ☆24Updated 2 years ago
• lucidrains / compositional-attention-pytorch
  Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process wi…
  ☆51Updated 3 years ago
• graphcore-research / out-of-the-box-fp8-training
  Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
  ☆45Updated 11 months ago