Glm

xLLM is a high-performance inference engine optimized for LLM, VLM, and other AI models, specifically designed for Chinese AI accelerators and...

InferenceX is an open-source continuous inference benchmarking research platform that tracks real-time performance of LLM inference frameworks across...

TokenSpeed is a specialized LLM inference engine optimized for agentic workloads, combining TensorRT-LLM-level performance with vLLM-level usability....

SGLang is a high-performance inference serving framework optimized for large language models and multimodal models, with support for speculative...

Command Code is an AI-powered coding agent that generates full-stack software projects, features, bug fixes, tests, and refactors while learning...

Unvanquished is a free, open-source FPS/RTS hybrid game built on the Daemon engine, continuing the legacy of Tremulous with decades of active...

CoStrict is an enterprise-focused, open-source AI coding assistant offering strict mode code generation, repository-wide code review, and code...

LobeHub is a self-hostable multi-agent orchestration platform that lets users deploy, schedule, and coordinate AI agents from multiple providers...

Parallax is a distributed inference framework that enables decentralized LLM serving across heterogeneous devices using P2P communication and...

GLM-OCR is a multimodal OCR model for complex document understanding, achieving state-of-the-art performance on benchmark datasets with 0.9B...

Ollama is a local LLM runtime that lets developers and end users download, run, and interact with open-weight language models (Llama, Gemma,...

Hugging Face Transformers is the de facto standard Python library for accessing, fine-tuning, and deploying state-of-the-art pretrained models across...

A hands-on educational tutorial for building large language models (LLMs) from scratch using Python, covering foundational concepts through...

GLM-4.5 is a family of agentic foundation models from Zhipu AI emphasizing reasoning, coding, and agent capabilities across multiple parameter sizes...