Alternatives and similar repositories for flash-attention-v100

Users that are interested in flash-attention-v100 are comparing it to the libraries listed below

• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆89Updated 6 months ago
• mdy666 / mdy_triton
  ☆148Updated 4 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.
  ☆227Updated 3 months ago
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆267Updated 3 months ago
• OpenNLPLab / lightning-attention
  Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
  ☆330Updated 8 months ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆107Updated 7 months ago
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆62Updated last year
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆201Updated last month
• mdy666 / Qwen-Native-Sparse-Attention
  qwen-nsa
  ☆83Updated 3 weeks ago
• OpenPPL / ppl.llm.serving
  ☆129Updated 10 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆145Updated 2 months ago
• madsys-dev / deepseekv2-profile
  ☆149Updated 8 months ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆111Updated 3 months ago
• Ascend / AscendSpeed
  ☆79Updated last year
• ruikangliu / FlatQuant
  [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"
  ☆183Updated 3 weeks ago
• YuxueYang1204 / CudaDemo
  Implement custom operators in PyTorch with cuda/c++
  ☆73Updated 2 years ago
• Tlntin / qwen-ascend-llm
  ☆51Updated last year
• gogongxt / nano-sglang
  ☆40Updated 2 weeks ago
• AyakaGEMM / Hands-on-GEMM
  ☆143Updated last year
• DeepLink-org / dlinfer
  ☆64Updated 2 weeks ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆119Updated last year
• dhcode-cpp / NSA-pytorch
  DeepSeek Native Sparse Attention pytorch implementation
  ☆107Updated last month
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆145Updated last year
• Starmys / TritonStudyGroup
  ☆86Updated last month
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆126Updated last year
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆283Updated last year
• InternLM / turbomind
  ☆97Updated 7 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆85Updated 4 months ago
• OpenPPL / ppl.llm.kernel.cuda
  ☆150Updated 10 months ago