zjing14

Pinned Repositories

AITemplate
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
Language:Python4.6k 82 244373
FBGEMM
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
Language:C++1.2k 66 174521
MIOpen
AMD's Machine Intelligence Library
Language:Assembly1.1k 91 1.1k233
AITemplate
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
Language:Python1 0 00
composable_kernel
Language:C++2 0 01
CTC
Language:C++1 1 03
DeepBench
Benchmarking Deep Learning operations on different hardware
Language:C++1 1 00
FBGEMM
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
Language:C++0 0 00
llvm-project-mlir
1 0 00
mlir_roundtrip
Language:C++1 1 00

zjing14's Repositories

zjing14/composable_kernel
Language:C++2 0 01
zjing14/AITemplate
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
Language:Python1 0 00
zjing14/CTC
Language:C++1 1 03
zjing14/DeepBench
Benchmarking Deep Learning operations on different hardware
Language:C++1 1 00
zjing14/llvm-project-mlir
1 0 00
zjing14/mlir_roundtrip
Language:C++1 1 00
zjing14/FBGEMM
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
Language:C++0 0 00