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.
cutlass
CUDA Templates for Linear Algebra Subroutines
EnergonAI
Large-scale model inference.
FastFold
Optimizing Protein Structure Prediction Model Training and Inference on GPU Clusters
nccl
Optimized primitives for collective multi-GPU communication
onnx
Open standard for machine learning interoperability
test
diffusion-benchmark
oneflow
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
liujuncheng's Repositories
liujuncheng/nccl
Optimized primitives for collective multi-GPU communication
liujuncheng/test
liujuncheng/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.
liujuncheng/cutlass
CUDA Templates for Linear Algebra Subroutines
liujuncheng/EnergonAI
Large-scale model inference.
liujuncheng/FastFold
Optimizing Protein Structure Prediction Model Training and Inference on GPU Clusters
liujuncheng/onnx
Open standard for machine learning interoperability
liujuncheng/openfold
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
liujuncheng/Uni-Core
an efficient distributed PyTorch framework