FlashMLA: Efficient Multi-head Latent Attention Kernels

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

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone

LLMPerf is a library for validating and benchmarking LLMs

FireAct: Toward Language Agent Fine-tuning

RayLLM - LLMs on Ray (Archived). Read README for more info.

Numbers every LLM developer should know

🦜🔗 Build context-aware reasoning applications

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

🌍 针对小白的算法训练 | 包括四部分：①.大厂面经 ②.力扣图解 ③.千本开源电子书 ④.百张技术思维导图（项目花了上百小时，希望可以点 star 支持，🌹感谢~）推荐免费ChatGPT使用网站

Everything you need in order to get YOLOv3 up and running in the cloud. Learn to train your custom YOLOv3 object detector in the cloud for free!

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

A curated list of deep learning resources for computer vision

A cloud-native open-source unified multi-cloud and hybrid-cloud platform. 开源、云原生的多云管理及混合云融合平台

Repo for counting stars and contributing. Press F to pay respect to glorious developers.