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
  ☆86Updated 6 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.
  ☆220Updated 2 months ago
• OpenNLPLab / lightning-attention
  Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
  ☆329Updated 7 months ago
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆266Updated 2 months ago
• mdy666 / mdy_triton
  ☆147Updated 3 months ago
• Ascend / AscendSpeed
  ☆79Updated last year
• shreyansh26 / FlashAttention-PyTorch
  Implementation of FlashAttention in PyTorch
  ☆171Updated 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…
  ☆198Updated this week
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆62Updated 11 months ago
• madsys-dev / deepseekv2-profile
  ☆148Updated 7 months ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆108Updated 3 months ago
• DeepLink-org / dlinfer
  ☆63Updated last month
• yuunnn-w / RWKV_Pytorch
  This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation…
  ☆130Updated last year
• 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
  ☆80Updated 2 months ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆107Updated 6 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆115Updated last year
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆361Updated this week
• Tlntin / qwen-ascend-llm
  ☆50Updated 11 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆143Updated last year
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆70Updated 2 years ago
• pprp / Awesome-Efficient-MoE
  Efficient Mixture of Experts for LLM Paper List
  ☆136Updated 2 weeks ago
• Ascend / pytorch
  Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch
  ☆437Updated last month
• InternLM / turbomind
  ☆95Updated 6 months ago
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆136Updated 9 months ago
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆132Updated 2 years ago
• PFCCLab / Camp
  飞桨护航计划集训营
  ☆21Updated 2 months ago
• OpenPPL / ppl.llm.serving
  ☆129Updated 9 months ago
• Tencent / AngelSlim
  Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
  ☆160Updated 2 weeks ago
• ModelTC / LightCompress
  A powerful toolkit for compressing large models including LLM, VLM, and video generation models.
  ☆585Updated last month