Alternatives and similar repositories for flex_head_fa

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

• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆216Updated 6 months ago
• PiotrNawrot / nano-sparse-attention
  The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
  ☆62Updated 4 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆126Updated 6 months ago
• Dao-AILab / grouped-latent-attention
  ☆53Updated this week
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆115Updated this week
• shawntan / stickbreaking-attention
  Stick-breaking attention
  ☆56Updated 2 months ago
• fla-org / flame
  🔥 A minimal training framework for scaling FLA models
  ☆146Updated 3 weeks ago
• FasterDecoding / TEAL
  ☆129Updated 3 months ago
• OpenNLPLab / LASP
  Linear Attention Sequence Parallelism (LASP)
  ☆83Updated 11 months ago
• epfml / dynamic-sparse-flash-attention
  ☆144Updated 2 years ago
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …
  ☆59Updated 7 months ago
• PiotrNawrot / sparse-frontier
  Official implementation of "The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs"
  ☆32Updated last month
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆155Updated last week
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆94Updated 2 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆75Updated 8 months ago
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆132Updated 9 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆107Updated 2 weeks ago
• insuhan / hyper-attn
  ☆81Updated last year
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆58Updated last year
• stanford-futuredata / stk
  ☆105Updated 9 months ago
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆43Updated 8 months ago
• alexzhang13 / flashattention2-custom-mask
  Triton implementation of FlashAttention2 that adds Custom Masks.
  ☆117Updated 9 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆163Updated 10 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆116Updated 6 months ago
• dame-cell / Triformer
  Transformers components but in Triton
  ☆33Updated 3 weeks ago
• sustcsonglin / linear-attention-and-beyond-slides
  ☆74Updated 3 months ago
• sustcsonglin / fla-tilelang
  ☆21Updated 2 months ago
• IST-DASLab / QuEST
  Work in progress.
  ☆67Updated this week
• OpenSparseLLMs / Linear-MoE
  ☆93Updated 2 weeks ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆46Updated 7 months ago