Alternatives and similar repositories for one-fx

Users that are interested in one-fx are comparing it to the libraries listed below

• Oneflow-Inc / oneflow_convert
  OneFlow->ONNX
  ☆43Updated 2 years ago
• Adlik / model_zoo
  ☆11Updated last week
• Oneflow-Inc / oneflow-lite
  ☆18Updated last year
• Oneflow-Inc / serving
  OneFlow Serving
  ☆20Updated 3 months ago
• Oneflow-Inc / oneflow-xrt
  ☆23Updated 2 years ago
• yester31 / Cutlass_EX
  study of cutlass
  ☆22Updated 8 months ago
• BBuf / megatron-lm-parallel-group-playground
  ☆16Updated last year
• BBuf / oneflow-cifar
  ☆13Updated 2 years ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆74Updated 11 months ago
• OpenPPL / ppl.kernel.cuda
  ☆37Updated 9 months ago
• DeepLink-org / CVFusion
  CVFusion is an open-source deep learning compiler to fuse the OpenCV operators.
  ☆31Updated 2 years ago
• RiseAI-Sys / DAX
  High performance inference engine for diffusion models
  ☆26Updated last week
• Oneflow-Inc / vision
  Datasets, Transforms and Models specific to Computer Vision
  ☆87Updated last year
• octoml / deformable-attention-kernel
  TVMScript kernel for deformable attention
  ☆25Updated 3 years ago
• ModelTC / pyvlova
  Yet another Polyhedra Compiler for DeepLearning
  ☆19Updated 2 years ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆94Updated 3 weeks ago
• Oneflow-Inc / oneflow-documentation
  oneflow documentation
  ☆69Updated last year
• AlibabaPAI / FLASHNN
  ☆96Updated 11 months ago
• LeiWang1999 / TVM.CMakeExtend
  Tutorials of Extending and importing TVM with CMAKE Include dependency.
  ☆14Updated 9 months ago
• vipshop / cache-dit
  🤗A Training-free and Easy-to-use Cache Acceleration Toolbox for Diffusion Transformers.
  ☆117Updated this week
• Oneflow-Inc / conda-env
  ☆12Updated 2 years ago
• L1aoXingyu / llm-infer-bench
  ☆11Updated last year
• OpenPPL / ppl.kernel.cpu
  ☆17Updated last year
• megvii-research / IntLLaMA
  IntLLaMA: A fast and light quantization solution for LLaMA
  ☆18Updated 2 years ago
• MegEngine / mgeconvert
  MegEngine到其他框架的转换器
  ☆70Updated 2 years ago
• ModelTC / NART
  NART = NART is not A RunTime, a deep learning inference framework.
  ☆37Updated 2 years ago
• megvii-research / basecls
  A codebase & model zoo for pretrained backbone based on MegEngine.
  ☆33Updated 2 years ago
• MARD1NO / CUDA-PPT
  ☆102Updated 4 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• MegEngine / cutlass
  CUDA Templates for Linear Algebra Subroutines
  ☆100Updated last year