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
  ☆80Updated 4 months ago
• Ascend / AscendSpeed
  ☆79Updated last year
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆60Updated 9 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.
  ☆211Updated 3 weeks ago
• DeepLink-org / dlinfer
  ☆54Updated this week
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆263Updated 3 weeks ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆104Updated last month
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆112Updated last year
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆105Updated 4 months ago
• mdy666 / mdy_triton
  ☆143Updated last month
• OpenNLPLab / lightning-attention
  Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
  ☆326Updated 6 months ago
• madsys-dev / deepseekv2-profile
  ☆146Updated 5 months ago
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆130Updated 2 years ago
• OpenPPL / ppl.nn.llm
  ☆141Updated last year
• Tencent / AngelSlim
  Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
  ☆100Updated this week
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆347Updated last week
• InternLM / turbomind
  ☆93Updated 5 months ago
• OpenPPL / ppl.llm.serving
  ☆128Updated 8 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆278Updated last year
• pprp / ultrascale-playbook-zh
  UltraScale Playbook 中文版
  ☆71Updated 5 months ago
• casper-hansen / AutoAWQ_kernels
  ☆78Updated 9 months ago
• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆175Updated this week
• Tlntin / qwen-ascend-llm
  ☆49Updated 10 months ago
• shreyansh26 / FlashAttention-PyTorch
  Implementation of FlashAttention in PyTorch
  ☆164Updated 7 months ago
• PFCCLab / Camp
  飞桨护航计划集训营
  ☆21Updated 3 weeks ago
• AyakaGEMM / Hands-on-GEMM
  ☆138Updated last year
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆138Updated last week
• AlibabaPAI / FLASHNN
  ☆98Updated 11 months ago
• LDLINGLINGLING / nano_vllm_note
  注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能
  ☆39Updated 3 weeks ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆138Updated this week