A high-throughput and memory-efficient inference and serving engine
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Interact with your documents using the power of GPT
Access large language models from the command-line
Open source libraries and APIs to build custom preprocessing pipelines
Open-source observability for your LLM application
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
Universal LLM Deployment Engine with ML Compilation
Open-source AI hackers to find and fix your app’s vulnerabilities
Compress tool outputs, logs, files, and RAG chunks
Agentic, Reasoning, and Coding (ARC) foundation models
Advanced language and coding AI model
AirLLM 70B inference with single 4GB GPU
Qwen2.5-VL is the multimodal large language model series
Adding guardrails to large language models
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon
All-in-one WebUI for AI generative image and video creation
Parallax is a distributed model serving framework
CNCF Sandbox Project
An open-source, modern-design AI training tracking and visualization
Collect, organize, use, and share, all in OmniBox
The official repo of Qwen chat & pretrained large language model
Operating LLMs in production
An orchestration framework for agentic AI and LLM applications
Uncertainty Quantification for Language Models, is a Python package