zwshan's repositories
DI-hpc
OpenDILab RL HPC OP Lib
haste
Haste: a fast, simple, and open RNN library
lsm
使用 Go 实现一个 LSM Tree 数据库
deepnano-blitz
Very fast ONT basecaller
neural-boost
Neural Boost targeting to boost inference performance.
qimera
Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples [NeurIPS 2021]
crf
Simple implementation of Conditional Random Fields (CRF) in Python. A faster, more powerful, Cython implementation is available in the vocrf project https://github.com/timvieira/vocrf
cudaFlow-benchmarks
Benchmarks for cudaFlow/cudaFlowCapturer
NN-CUDA-Example
Several simple examples for popular neural network toolkits calling custom CUDA operators.
Optimizing-LSTMs-on-GPU
Implementation of the paper "Optimizing Performance of Recurrent Neural Networks on GPUs" in CUDA and OpenMP.
ArrayLSTM
GPU/CPU (CUDA) Implementation of "Recurrent Memory Array Structures", Simple RNN, LSTM, Array LSTM..
Basecalling-comparison
A comparison of different Oxford Nanopore basecallers
cuDNN-sample
cuDNN sample codes provided by Nvidia
HybridFS
Hybrid File System : SSD+HDD
hybridFS-SSD-and-HDD
It provides a single namespace combining SSD and HDD