Sourcetrail - free and open-source interactive source explorer

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

CUDA Templates for Linear Algebra Subroutines

Stable Diffusion and Flux in pure C/C++

LightSeq: A High Performance Library for Sequence Processing and Generation

清华大学计算机系课程攻略

【A common used C++ DAG framework】 一个通用的、无三方依赖的、跨平台的、收录于awesome-cpp的、基于流图的并行计算框架。欢迎star & fork & 交流

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052

校招、秋招、春招、实习好项目，带你从零动手实现支持LLama的大模型推理框架。

Official implementation of ID-unaware Deepfake Detection Model

A Reinforcement-Learning based Renju game

using TensorRT API to develop and deploy model with C++ or python