Alternatives and similar repositories for sgl-flash-attn

Users that are interested in sgl-flash-attn are comparing it to the libraries listed below

• li-plus / flash-preference

  View on GitHub
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆51Jul 4, 2025Updated 7 months ago
• zhuzilin / flash-attention-with-sink

  View on GitHub
  ☆38Aug 7, 2025Updated 6 months ago
• ademeure / DeeperGEMM

  View on GitHub
  DeeperGEMM: crazy optimized version
  ☆73May 5, 2025Updated 9 months ago
• NoakLiu / FastCache-xDiT

  View on GitHub
  FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]
  ☆46Jan 27, 2026Updated 2 weeks ago
• sail-sg / SkyLadder

  View on GitHub
  The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
  ☆42Dec 29, 2025Updated last month
• NickL77 / BaldEagle

  View on GitHub
  3x Faster Inference; Unofficial implementation of EAGLE Speculative Decoding
  ☆83Jul 3, 2025Updated 7 months ago
• ByteDance-Seed / FlexPrefill

  View on GitHub
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆160Oct 13, 2025Updated 4 months ago
• svg-project / flash-kmeans

  View on GitHub
  Fast and memory-efficient exact kmeans
  ☆138Updated this week
• microsoft / RetrievalAttention

  View on GitHub
  Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
  ☆122Jan 1, 2026Updated last month
• tilde-research / nsa-impl

  View on GitHub
  An efficient implementation of the NSA (Native Sparse Attention) kernel
  ☆129Jun 24, 2025Updated 7 months ago
• sgl-project / genai-bench

  View on GitHub
  Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…
  ☆266Updated this week
• saubury / GenPiCam

  View on GitHub
  GenPiCam - a RaspberryPi based camera that reimagines the world with GenAI.
  ☆10Jun 28, 2023Updated 2 years ago
• AdaptInfer / context-review

  View on GitHub
  ☆14Jan 23, 2026Updated 3 weeks ago
• Yifei-Zuo / Flash-LLA

  View on GitHub
  Official repository for the paper Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regressi…
  ☆23Oct 1, 2025Updated 4 months ago
• SuDIS-ZJU / nlcTables

  View on GitHub
  ☆15Jan 27, 2026Updated 2 weeks ago
• ChuanyangZheng / L2ViT

  View on GitHub
  Official PyTorch implementation of The Linear Attention Resurrection in Vision Transformer
  ☆15Sep 7, 2024Updated last year
• lspecian / vexfs

  View on GitHub
  VexFS is a Linux kernel-native file system with built-in vector search and semantic memory. Designed for AI agents, RAG, and LLM workload…
  ☆24Oct 19, 2025Updated 3 months ago
• oliverhu / rama

  View on GitHub
  llama2 inference engine in Rust
  ☆13Apr 12, 2024Updated last year
• LGAI-Research / SetR

  View on GitHub
  ☆20Sep 11, 2025Updated 5 months ago
• deathwings602 / Unified-IR

  View on GitHub
  面向多平台编译优化的深度学习中间表示
  ☆10Oct 28, 2024Updated last year
• DerrickYLJ / TidalDecode

  View on GitHub
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆52Aug 6, 2025Updated 6 months ago
• meeuw / unattended-windows-10

  View on GitHub
  Packer templates to install Windows 10 Evaluation using the qemu/kvm builder.
  ☆12Sep 2, 2021Updated 4 years ago
• SuDIS-ZJU / Data-Quality-for-Vision-Language-Models

  View on GitHub
  ☆29Nov 18, 2025Updated 2 months ago
• yuxiang-gao / awesome-llm-blogs

  View on GitHub
  Blogs that I'm actively following.
  ☆13Sep 17, 2023Updated 2 years ago
• MLSysOps / InfraGym

  View on GitHub
  Empowering LLM Agents for Real-World Computer System Optimization
  ☆16Sep 10, 2025Updated 5 months ago
• GAIR-NLP / DatasetResearch

  View on GitHub
  DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery
  ☆20Sep 24, 2025Updated 4 months ago
• Halifuda / Xerxes

  View on GitHub
  A standalone CXL-enabled system simulator.
  ☆18Jan 10, 2026Updated last month
• zejia-lin / BulletServe

  View on GitHub
  Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration
  ☆33Jan 8, 2026Updated last month
• kvignesh1420 / cot-icl-lab

  View on GitHub
  [ACL 2025] Official implementation of the "CoT-ICL Lab" framework
  ☆11Oct 10, 2025Updated 4 months ago
• GeeeekExplorer / 3d-parallel-demo

  View on GitHub
  使用torch.distributed实现DP/TP/PP
  ☆12Dec 28, 2023Updated 2 years ago
• zyxxmu / cam

  View on GitHub
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆49Jun 19, 2024Updated last year
• shyhoom / T22_034_CRDDC_2022_SourceCode

  View on GitHub
  T22_034_han_shi_hao_CRDDC_2022_SourceCode
  ☆11Dec 29, 2023Updated 2 years ago
• NetManAIOps / DOMI_code

  View on GitHub
  code for DOMI
  ☆11Mar 24, 2023Updated 2 years ago
• Elluran / concentration_notebooks

  View on GitHub
  ☆11Dec 11, 2024Updated last year
• AniZpZ / smoothquant

  View on GitHub
  [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
  ☆11Dec 13, 2023Updated 2 years ago
• MoFHeka / execution-ucx

  View on GitHub
  A std::execution style runtime context and High Performance RPC Transport for using OpenUCX. Including CUDA/ROCM/... devices with RDMA.
  ☆29Updated this week
• metadriverse / AIM

  View on GitHub
  ☆13Jul 23, 2025Updated 6 months ago
• homeport / yft

  View on GitHub
  /j f t/ - YAML file tool
  ☆13Apr 5, 2025Updated 10 months ago
• ThoughtWorksInc / dataclouds

  View on GitHub
  Blog for dataclouds@thoughtworks.
  ☆10Jun 19, 2016Updated 9 years ago