Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

Expert Parallelism Load Balancer

FlashMLA: Efficient MLA decoding kernels

A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, and more.

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

structured outputs for llms

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…

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

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Supercharge Your LLM Application Evaluations 🚀

Collections of vector search related libraries, service and research papers

A fast, powerful, safe and lightweight scripting language and engine for .NET

A natural language interface for computers

A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.

A tool that transforms OpenAI API requests into Azure OpenAI API requests, allowing OpenAI-compatible applications to seamlessly use Azure OpenAI. 一个 OpenAI API 的代理工具，能将 OpenAI API 请求转为 Azure OpenA…

React component to create graphic user interface with: - draggable nodes with ports and edges on a directed graph editor. - extensibility to customize the widgets or behaviors. - accessbility and t…