Alternatives and similar repositories for FlashMHA

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

• OpenNLPLab / LASP
  Linear Attention Sequence Parallelism (LASP)
  ☆85Updated last year
• BBuf / flash-rwkv
  ☆31Updated last year
• pprp / Pruner-Zero
  [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs
  ☆91Updated 7 months ago
• keshik6 / grafting
  Exploring Diffusion Transformer Designs via Grafting
  ☆45Updated last month
• rayleizhu / vllm-ra
  [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts
  ☆40Updated last year
• tridao / flash-attention-wheels
  ☆51Updated last year
• SprocketLab / sparse_matrix_fine_tuning
  Official repository for ICML 2024 paper "MoRe Fine-Tuning with 10x Fewer Parameters"
  ☆20Updated 2 months ago
• JerryYin777 / Cross-Layer-Attention
  Self Reproduction Code of Paper "Reducing Transformer Key-Value Cache Size with Cross-Layer Attention (MIT CSAIL)
  ☆17Updated last year
• thunlp / SparsingLaw
  The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".
  ☆23Updated 8 months ago
• sustcsonglin / linear-attention-and-beyond-slides
  ☆77Updated 4 months ago
• kyegomez / Hedgehog
  Implementation of the model "Hedgehog" from the paper: "The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry"
  ☆14Updated last year
• Infini-AI-Lab / gsm_infinite
  ☆48Updated last month
• 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
• YuchuanTian / DiJiang
  [ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear at…
  ☆101Updated last year
• eth-easl / fmengine
  Utilities for Training Very Large Models
  ☆58Updated 9 months ago
• RWKV / RWKV-LM
  RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…
  ☆50Updated 4 months ago
• Dao-AILab / grouped-latent-attention
  ☆119Updated last month
• fla-org / flash-bidirectional-linear-attention
  Triton implement of bi-directional (non-causal) linear attention
  ☆52Updated 5 months ago
• facebookresearch / adaptive_scheduling
  Experimental scripts for researching data adaptive learning rate scheduling.
  ☆23Updated last year
• jiwonsong-dev / ReasoningPathCompression
  Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"
  ☆19Updated last month
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆42Updated 2 weeks ago
• TianjinYellow / StableSPAM
  ☆22Updated 3 months ago
• yuzhenmao / IceFormer
  Implementation of IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).
  ☆25Updated this week
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆142Updated last month
• hao-ai-lab / Awesome-Video-Attention
  A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…
  ☆28Updated this week
• UCDvision / NOLA
  Code for NOLA, an implementation of "nola: Compressing LoRA using Linear Combination of Random Basis"
  ☆56Updated 10 months ago
• zhixuan-lin / forgetting-transformer
  [ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"
  ☆116Updated 2 weeks ago
• Lyken17 / hf-torrent
  ☆39Updated last year
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆60Updated last year
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆55Updated 11 months ago