whutbd Goto Github PK

deepctr

deepctr-torch

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

deepmatch-torch

「PyTorch」A deep matching model library for recommendations & advertising. It's easy to train models and to export representation vectors which can be used for ANN search.

deeprec

DeepRec is a recommendation engine based on TensorFlow.

deepspeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

diskann

Scalable graph based indices for approximate nearest neighbor search

dssm

Implementation of DSSM for recommendation by PyTorch (Including SENet and random negative sampling)

faiss

A library for efficient similarity search and clustering of dense vectors.

fastertransformer

Transformer related optimization, including BERT, GPT

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

fastmemcpy

Speed-up over 50% in average vs traditional memcpy in gcc 4.9 or vc2012

fasttext

Library for fast text representation and classification.

flashinfer

FlashInfer: Kernel Library for LLM Serving

flatbuffers

FlatBuffers: Memory Efficient Serialization Library

fun-rec

推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/

gflags

The gflags package contains a C++ library that implements commandline flags processing. It includes built-in support for standard types such as string and the ability to define flags in the source file in which they are used. Online documentation available at:

ggml-tutorial

glog

C++ implementation of the Google logging module

google-research

Google Research

graph-learn

An Industrial Graph Neural Network Framework

havenask

hnswlib

Header-only C++/python library for fast approximate nearest neighbors

horovod

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

how-to-optim-algorithm-in-cuda

Cuda Learn Samples

how_to_optimize_in_gpu

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

incubator-brpc

Industrial-grade RPC framework used throughout Baidu, with 1,000,000+ instances and thousands kinds of services. "brpc" means "better RPC".

incubator-kvrocks

Kvrocks is a distributed key value NoSQL database that uses RocksDB as storage engine and is compatible with Redis protocol.

kmeans-gmm-hmm

HMM based on KMeans and GMM

knowhere

Knowhere is an open-source vector search engine, it integrates FAISS, HNSW and Annoy

learning_cuda