Juncheng (liujuncheng)

liujuncheng

Geek Repo

Company:OneFlow

Location:Beijing

Github PK Tool:Github PK Tool

Juncheng's repositories

nccl

Optimized primitives for collective multi-GPU communication

Language:CudaLicense:NOASSERTIONStargazers:1Issues:2Issues:0
Stargazers:1Issues:0Issues:0

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:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

cutlass

CUDA Templates for Linear Algebra Subroutines

Language:C++License:NOASSERTIONStargazers:0Issues:1Issues:0

EnergonAI

Large-scale model inference.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

FastFold

Optimizing Protein Structure Prediction Model Training and Inference on GPU Clusters

Language:CudaLicense:Apache-2.0Stargazers:0Issues:1Issues:0

onnx

Open standard for machine learning interoperability

Language:C++License:Apache-2.0Stargazers:0Issues:1Issues:0

openfold

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

Uni-Core

an efficient distributed PyTorch framework

Language:PythonLicense:MITStargazers:0Issues:1Issues:0