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
  ☆99Updated last month
• 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 last week
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆274Updated 5 months ago
• Ascend / AscendSpeed
  ☆79Updated 2 years ago
• mdy666 / mdy_triton
  ☆152Updated 6 months ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆114Updated 6 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…
  ☆223Updated 2 weeks ago
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆64Updated last year
• dhcode-cpp / NSA-pytorch
  DeepSeek Native Sparse Attention pytorch implementation
  ☆114Updated last month
• madsys-dev / deepseekv2-profile
  ☆155Updated 10 months ago
• DeepLink-org / dlinfer
  ☆74Updated last week
• shreyansh26 / FlashAttention-PyTorch
  Implementation of FlashAttention in PyTorch
  ☆180Updated last year
• Tencent / AngelSlim
  Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
  ☆309Updated this week
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆148Updated last year
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆110Updated 9 months ago
• gogongxt / nano-sglang
  ☆116Updated 3 weeks ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆120Updated last year
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆105Updated this week
• OpenNLPLab / lightning-attention
  Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
  ☆339Updated 11 months ago
• yuunnn-w / RWKV_Pytorch
  This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation…
  ☆132Updated last year
• Tlntin / qwen-ascend-llm
  ☆55Updated last year
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆135Updated 2 years ago
• OpenPPL / ppl.llm.serving
  ☆130Updated last year
• ModelTC / LightCompress
  [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
  ☆672Updated 2 months ago
• dsl-learn / triton-tutorial
  Getting Started with Triton: A Tutorial for Python Beginners
  ☆33Updated 3 months ago
• zhaochenyang20 / ModelServer
  Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
  ☆61Updated last year
• OpenPPL / ppl.nn.llm
  ☆141Updated last year
• flagos-ai / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆287Updated last year
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆137Updated last year
• YuxueYang1204 / CudaDemo
  Implement custom operators in PyTorch with cuda/c++
  ☆76Updated 3 years ago