xiang1563

tiny-universe

《大模型白盒子构建指南》：一个全手搓的Tiny-Universe

mmdetection-annotated

mmdetection源码注释

Jash-good-idea-20200304-001

耕莘護專 ~ 示範的3D口罩折法(Jash-good-idea-20200304-001)

PGL

Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle

cv_learning_resnet50

DeepSpeed

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

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Paddle-Inference-Demo

DeepLearningBookQA_cn

深度学习面试问题 回答对应的DeepLearning中文版页码

DL-Notes-for-Interview

deep learning/ machine learning

interview

📚 C/C++ 技术面试基础知识总结，包括语言、程序库、数据结构、算法、系统、网络、链接装载库等知识及面试经验、招聘、内推等信息。This repository is a summary of the basic knowledge of recruiting job seekers and beginners in the direction of C/C++ technology, including language, program library, data structure, algorithm, system, network, link loading library, interview experience, recruitment, recommendation, etc.

nmslib

Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.

pytorch-handbook

pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

tiny-cuda-nn

Lightning fast C++/CUDA neural network framework

awesome-project-ideas

Curated list of Machine Learning, NLP, Vision, Recommender Systems Project Ideas

tiny-gpu

A minimal GPU design in Verilog to learn how GPUs work from the ground up

llm.c

LLM training in simple, raw C/CUDA

MyTinySTL

Achieve a tiny STL in C++11

simdjson

Parsing gigabytes of JSON per second : used by Facebook/Meta Velox, the Node.js runtime, ClickHouse, WatermelonDB, Apache Doris, Milvus, StarRocks

fast-llama

Runs LLaMA with Extremely HIGH speed

PaddleDetection

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

brpc_source_code_analysis

brpc源码分析

gparallel

A DAG based parallel task schedule framework for galois advertising｜基于DAG(Directed Acyclic Graph)的并行任务调度系统，自动推导节点依赖生成DAG。

My-Linux-Config

:clap: Modern neovim configuration based on native lsp

so-vits-svc

SoftVC VITS Singing Voice Conversion

Makefile-Tutorial-zh-CN

Makefile 教程