A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Multilingual Voice Understanding Model

LLM training in simple, raw C/CUDA

The NVIDIA RTX™ AI Toolkit is a suite of tools and SDKs for Windows developers to customize, optimize, and deploy AI models across RTX PCs and cloud.

一个简单的本地网页界面，直接使用ChatTTS将文字合成为语音，同时支持对外提供API接口。

Open-Sora: Democratizing Efficient Video Production for All

Unify Efficient Fine-tuning of 100+ LLMs

Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind

A real-time motion capture system for 3D virtual character animating.

yolov5 车牌检测 车牌识别 中文车牌识别 检测 支持12种中文车牌 支持双层车牌

中国大模型

Real-time speech recognition using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Raspberry Pi, VisionFive2, etc.

Deep Learning System core principles introduction.

🔥 [PR 2023] Multi-scale Attention Guided Pose Transfer (official code).

Inference Llama 2 in one file of pure C

Accelerated SMPL operation, commonly used in generate 3D human mesh, STAR included.

We extend CoT data to Alpaca to boost its reasoning ability. We are constantly expanding our collection of instruction-tuning data. The instruction collection can be found at https://huggingface.co…

Making large AI models cheaper, faster and more accessible

Train transformer language models with reinforcement learning.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Monocular, One-stage, Regression of Multiple 3D People, ROMP[ICCV21], BEV[CVPR22]

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Multi-object tracking and segmentation using YOLOv8

🍰🍎ColugoMum: Intelligent Retail Settlement Platform can accurately locate and identify each commodity, and can return a complete shopping list and the actual total price of commodities that custome…

An Blender addon uses ROMP to extract human's 3D poses from image, video or webcam and drive your own 3D character.

Our insights of Openpilot, a deepdive project on it