Alternatives and similar repositories for PaddleCustomDevice

Users that are interested in PaddleCustomDevice are comparing it to the libraries listed below

• PaddlePaddle / community
  PaddlePaddle Developer Community
  ☆113Updated last week
• PaddlePaddle / CINN
  Compiler Infrastructure for Neural Networks
  ☆146Updated last year
• PaddlePaddle / Paddle-Inference-Demo
  ☆262Updated 3 weeks ago
• OpenPPL / ppl.llm.kernel.cuda
  ☆148Updated 5 months ago
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆57Updated 7 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• CalvinXKY / BasicCUDA
  A tutorial for CUDA&PyTorch
  ☆146Updated 5 months ago
• Oneflow-Inc / oneflow_convert
  OneFlow->ONNX
  ☆43Updated 2 years ago
• OpenPPL / ppl.pmx
  ☆58Updated 7 months ago
• OpenPPL / ppl.llm.serving
  ☆128Updated 6 months ago
• Cambricon / mlu-ops
  Efficient operation implementation based on the Cambricon Machine Learning Unit (MLU) .
  ☆123Updated this week
• OpenPPL / ppl.kernel.cuda
  ☆36Updated 8 months ago
• AyakaGEMM / Hands-on-GEMM
  ☆135Updated last year
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆126Updated 5 months ago
• zjhellofss / KuiperCourse
  b站上的课程
  ☆76Updated last year
• FlagOpen / FlagCX
  ☆69Updated this week
• PaddlePaddle / benchmark
  ☆78Updated 3 weeks ago
• wangzyon / trt_learn
  TensorRT encapsulation, learn, rewrite, practice.
  ☆28Updated 2 years ago
• xiatwhu / trt2023
  ☆26Updated last year
• triton-inference-server / paddlepaddle_backend
  ☆35Updated last year
• MegEngine / MegCC
  MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器
  ☆484Updated 8 months ago
• Tlntin / trt2023
  ☆26Updated last year
• BBuf / onnx_learn
  ☆99Updated 3 years ago
• luchangli03 / onnxsim_large_model
  simplify >2GB large onnx model
  ☆59Updated 6 months ago
• bug-developer021 / YOLOV5_optimization_on_triton
  Compare multiple optimization methods on triton to imporve model service performance
  ☆52Updated last year
• nicolaswilde / cuda-tensorcore-hgemm
  ☆146Updated 6 months ago
• harleyszhang / lite_llama
  A light llama-like llm inference framework based on the triton kernel.
  ☆128Updated last week
• HeKun-NVIDIA / TensorRT-Developer_Guide_in_Chinese
  ☆283Updated 3 years ago
• OpenPPL / ppl.cv
  ppl.cv is a high-performance image processing library of openPPL supporting various platforms.
  ☆504Updated 7 months ago
• torchpipe / torchpipe
  Serving Inside Pytorch
  ☆160Updated 2 weeks ago