kelly-zhe Goto Github PK

anything-llm

A multi-user ChatGPT for any LLMs and vector database. Unlimited documents, messages, and storage in one privacy-focused app. Now available as a desktop application with a built-in LLM!

awesome-programming-books

📚 经典技术书籍 PDF 文件，持续更新...

chatgpt-next-web

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。

coursera

cs5031-p1-hangman

dnn_processing

ffmpeg avfilter dnn model

ffmpeg

Mirror of https://git.ffmpeg.org/ffmpeg.git

ffmpeg-vaapi-openvino

Demo on iGPU for FFmpeg decode and scale, OpenVINO inference. this is zero-copy solution, which means No frame data copy from CPU to iGPU.

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.

introduction_to_ml_with_python

Notebooks and code for the book "Introduction to Machine Learning with Python"

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

localgpt

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

mediamtx

Ready-to-use SRT / WebRTC / RTSP / RTMP / LL-HLS media server and media proxy that allows to read, publish, proxy and record video and audio streams.

mingpt

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

openblas

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

other-works

paddle

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

paddle-lite

PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）

rasa_demo

tensorrt

NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.