I am Deep Learning Programmer

• Model optimization
  • Knowledge Distillation
  • Pruning
  • Quantization (ptq, qat)
• Parallel Programming
  • CUDA
  • SIMD

C/C++, CUDA, OpenCL, Python, Rust, Javascript, Java, C#, OpenMP

Pytorch, TensorFlow, Darknet, Cudnn, TensorRT, OpenVINO, OneDNN, Onnx runtime, Aparch TVM

Web, WebSocket, WebRTC, Nodejs, Django, MySQL, Anaconda, git, github, docker, Make, CMake, Nvidia edge device(jetson series, drive orin ...)

PinnedLoading

1. Cutlass_EXCutlass_EXPublic

   study of cutlass

   Cuda 21 4

2. Real_ESRGAN_TRTReal_ESRGAN_TRTPublic

   Real ESRGAN Optimization Using by TensorRT API, linux

   C++ 20 7

3. TensorRT_APITensorRT_APIPublic

   Deep Learning Model Optimization Using by TensorRT API, window

   Python 16 4

4. Quantization_EXQuantization_EXPublic

   quantization example for pqt & qat

   Python 6 2

5. GEMM_Conv2d_CUDAGEMM_Conv2d_CUDAPublic

   CUDA Gemm Convolution implementation

   C++ 6 1

6. Winograd_Conv2d_cppWinograd_Conv2d_cppPublic

   Winograd Convolution Implementation using by cpp

   C++ 6