AI-Infra-from-Zero-to-Hero vs ollama
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| AI-Infra-from-Zero-to-Hero | ollama | |
|---|---|---|
| Tagline | Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice | Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. |
| Stars | 4.2k | 176k |
| Forks | 399 | 17k |
| Open issues | 14 | 3.4k |
| Language | - | Go |
| License | MIT | MIT |
| Last pushed | Jul 25, 2025 | Jul 7, 2026 |
| Categories | Model Training, Inference & Serving, Developer Tools, AI Agents | AI Agents, LLM Frameworks |
AI-Infra-from-Zero-to-Hero
HuaizhengZhang/AI-Infra-from-Zero-to-Hero is a curated repository of research in machine learning systems, including Large Language Models (LLM) and Generative AI. It provides links to papers, resources, video tutorials, and categorizes information related to infrastructure for ML training, inference, and serving.
ollama
Ollama is a platform for deploying and interacting with various large language models (LLMs) such as Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, and Gemma on macOS, Windows, Linux, and Docker environments.
Go