Large Language Model Text Generation Inference

深度学习系统笔记，包含深度学习数学基础知识、神经网络基础部件详解、深度学习炼丹策略、模型压缩算法详解，以及如何实现深度学习推理框架实战。

Making large AI models cheaper, faster and more accessible

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

An End to End GenAI Framework

A high-throughput and memory-efficient inference and serving engine for LLMs

LLM inference in C/C++

Inference code for Llama models

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

搞定C++:punch:。C++ Primer 中文版第5版学习仓库，包括笔记和课后练习答案。

A faster implementation of PointNet++ based on PyTorch.

「Java学习+面试指南」一份涵盖大部分 Java 程序员所需要掌握的核心知识。准备 Java 面试，首选 JavaGuide！

A resource repository for 3D machine learning

Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

[CVPR2023] LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion

Official code base of the BEVDet series .

[CVPR2023] Official Implementation of "DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets"

关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative model各式各样研究的阅读笔记

[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496

高性能并行编程与优化 - 课件

Official implementation of our TIV'23 paper: Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders

Repo of "MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds".

CUDA Templates for Linear Algebra Subroutines

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

[CVPR 2022] SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation

1024 + 深度强化学习（Deep Reinforcement Learning + 1024 Game)

Implementation for CenterFormer: Center-based Transformer for 3D Object Detection (ECCV 2022)