主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Real-time and accurate open-vocabulary end-to-end object detection

YOLOv8 TensorRT C++ Implementation

how to optimize some algorithm in cuda.

FlashInfer: Kernel Library for LLM Serving

[AAAI 2024 Oral] AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

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

TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its…

Material for gpu-mode lectures

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

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

🚀 你的YOLO部署神器。TensorRT Plugin、CUDA Kernel、CUDA Graphs三管齐下，享受闪电般的推理速度。| Your YOLO Deployment Powerhouse. With the synergy of TensorRT Plugins, CUDA Kernels, and CUDA Graphs, experience lightning-fast…

yolov10 目标检测部署版本，便于移植不同平台（onnx、tensorRT、rknn、Horizon），全网部署最简单、运行速度最快的部署方式（全网首发）。

用c++实现了yolov5使用openvino的部署

Let us control diffusion models!

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Official implementation of the paper "Diffusion-based Image Generation for In-distribution Data Augmentation in Surface Defect Detection" accepted @ VISAPP 2024.

Yao is an all-in-one application engine that enables developers to create web apps, REST APIs, enterprise apps, and more, with AI as a seamless collaborator.

Nightly release of ControlNet 1.1

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

WebUI extension for ControlNet