Stars
The Language Virtual Machine for Agent Skills
Run data collection, model fine-tuning, and real-world inference on the SO101 robotic arm ｜ 在 SO101 机械臂上跑通数据采集、模型微调和真机推理
TuGraph: A High Performance Graph Database.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
High-speed Large Language Model Serving for Local Deployment
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复