Alternatives and similar repositories for flash_attention:

Users that are interested in flash_attention are comparing it to the libraries listed below

• cloneofsimo / min-fsdp
  ☆78Updated 10 months ago
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆47Updated last year
• srush / mamba-primer
  ☆37Updated last year
• PiotrNawrot / sparse-frontier
  Official implementation of "The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs"
  ☆22Updated last week
• edwardmilsom / function-space-learning-rates-paper
  Code for the paper "Function-Space Learning Rates"
  ☆19Updated 3 weeks ago
• riverstone496 / awesome-second-order-optimization
  ☆26Updated last year
• radarFudan / mamba-minimal-jax
  ☆30Updated 5 months ago
• fal-ai-community / nano-mdm
  Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun
  ☆49Updated last month
• katiekang1998 / reasoning_generalization
  ☆31Updated 4 months ago
• ethansmith2000 / TransformerExperiments
  ☆19Updated last month
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆43Updated 7 months ago
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆27Updated last year
• google-deepmind / spectral_ssm
  ☆31Updated last year
• jiasenlu / LL3M
  LL3M: Large Language and Multi-Modal Model in Jax
  ☆72Updated last year
• RobertCsordas / moeut
  ☆78Updated 8 months ago
• test-time-training / ttt-tk
  ☆26Updated last month
• young-geng / mintext
  Minimal but scalable implementation of large language models in JAX
  ☆34Updated 6 months ago
• zhixuan-lin / forgetting-transformer
  [ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"
  ☆97Updated 3 weeks ago
• sail-sg / SkyLadder
  The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
  ☆29Updated last month
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated 11 months ago
• sjelassi / transformers_ssm_copy
  ☆31Updated last year
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆123Updated last year
• lucidrains / taylor-series-linear-attention
  Explorations into the recently proposed Taylor Series Linear Attention
  ☆99Updated 8 months ago
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆72Updated 4 months ago
• RobertCsordas / moe
  Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
  ☆37Updated last year
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆83Updated last year
• lucidrains / self-reasoning-tokens-pytorch
  Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto
  ☆55Updated 11 months ago
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• Laz4rz / mup
  Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation
  ☆12Updated this week
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆80Updated 5 months ago