Alternatives and similar repositories for flash-attention

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

• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆123Updated last month
• InternLM / turbomind
  ☆96Updated 10 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆219Updated 2 weeks ago
• madsys-dev / deepseekv2-profile
  ☆155Updated 10 months ago
• stepfun-ai / StepMesh
  ☆342Updated this week
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆148Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆120Updated last year
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆457Updated 8 months ago
• microsoft / sarathi-serve
  A low-latency & high-throughput serving engine for LLMs
  ☆471Updated 3 weeks ago
• AlibabaPAI / FLASHNN
  ☆105Updated last year
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆148Updated 8 months ago
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆92Updated last week
• flagos-ai / FlagCX
  FlagCX is a scalable and adaptive cross-chip communication library.
  ☆170Updated this week
• Azure / msccl-executor-nccl
  ☆47Updated last year
• KuangjuX / NVSHMEM-Tutorial
  NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer
  ☆158Updated 4 months ago
• antgroup / DeepXTrace
  DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.
  ☆91Updated 2 weeks ago
• abcdabcd987 / libfabric-efa-demo
  ☆76Updated last year
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆276Updated 6 months ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆233Updated 2 years ago
• microsoft / tokenweave
  Accepted to MLSys 2026
  ☆70Updated this week
• fzyzcjy / torch_memory_saver
  Allow torch tensor memory to be released and resumed later
  ☆213Updated 3 weeks ago
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆105Updated this week
• bytedance / xpu-perf
  AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…
  ☆298Updated 2 weeks ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆73Updated 8 months ago
• Victarry / PP-Schedule-Visualization
  Pipeline Parallelism Emulation and Visualization
  ☆77Updated 3 weeks ago
• WukLab / preble
  Stateful LLM Serving
  ☆95Updated 10 months ago
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆248Updated 2 weeks ago
• microsoft / mscclpp
  MSCCL++: A GPU-driven communication stack for scalable AI applications
  ☆457Updated this week
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆71Updated 4 months ago
• flagos-ai / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆287Updated last year