“optimization”

A legacy collection of libraries for optimizing AI model performance

OptiLLM is an OpenAI API-compatible optimizing inference proxy that enhances LLM accuracy and performance on reasoning tasks without needing to train or fine-tune models.

Unified framework for scaling AI and Python applications

Automatic Differentiation via Text

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

An interaction control harness optimized for controlled, consistent, and predictable LLM interactions for building reliable customer-facing AI agents.

The absolute trainer to light up AI agents.

GPU-optimized library for training transformer models at scale

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework

Context compression layer for AI agents

Repository for resources dedicated to Claude Code, an AI coding companion by Anthropic PBC.

The open source AI engineering platform for agents, LLMs, and ML models

Human-centric framework to build and manage AI/ML systems

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray

Uncover Your Agent's Blind Spots

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

Fully automatic censorship removal for language models

Universal LLM Deployment Engine with ML Compilation

Official repo of Qwen, a large language model by Alibaba Cloud.

Comprehensive tracing, automated evaluations, and production-ready dashboards for LLM applications.

Supercharge Your LLM Application Evaluations

The easiest way to serve AI apps and models

The official repository of Qwen-VL (通义千问-VL) – Large Vision-Language Model by Alibaba Cloud

🤖 Self-modifying Framework from the Future 🔮 World's First AMS