Open Source Project
Beginner
★ Featured
Ollama Local LLM Tool
Ollama · Deployment & Serving
Run open-source LLMs locally with a single command on Windows, macOS, or Linux — the go-to starting point for local deployment.
🚀 Deployment & Serving
Local inference, production serving, MLOps and engineering practice · 14 resources (14 checked)
🌱 AI Fundamentals📐 Machine Learning🔬 Deep Learning🧠 Large Language Models💬 Prompting & Apps💻 AI-Assisted Coding🤖 AI Agent Development🔌 MCP Protocol📚 RAG & Retrieval🚀 Deployment & Serving🏗️ Hands-on Projects🎨 Multimodal & AIGC🛠️ Open Source & Tools📰 Community & News🧰 Tools & API Platforms
Open Source Project
Advanced
vLLM Official Documentation
vLLM 社区 · Deployment & Serving
A high-performance LLM inference and serving engine; PagedAttention dramatically boosts throughput, with support for mainstream open-source models.
Open Source Project
Beginner
Open WebUI
Open WebUI · Deployment & Serving
A self-hosted AI chat interface that supports Ollama and OpenAI-compatible APIs, and can be deployed offline on an intranet.
Tool & Platform
Beginner
LM Studio Local Model Tool
LM Studio · Deployment & Serving
A GUI tool for running LLMs locally, with one-click model downloads and local chat — beginner friendly.
Open Source Project
Advanced
llama.cpp Inference Engine
ggerganov · Deployment & Serving
A pure C/C++ inference engine that runs LLMs even on CPU — one of the de facto standards for local deployment.
Open Source Project
Advanced
Hugging Face Text Generation Inference
Hugging Face · Deployment & Serving
Hugging Face's official inference serving framework with continuous batching and tensor parallelism, built for API-style deployment.
Official Docs
Beginner
Gradio Official Documentation
Gradio · Deployment & Serving
A Python library for ML demo interfaces — wrap a model into a shareable web app in a few lines.
Official Docs
Beginner
Streamlit Official Documentation
Streamlit · Deployment & Serving
A pure-Python framework for interactive web apps — a popular pick for AI prototypes and internal tools.
Open Source Project
Intermediate
MLflow Official Documentation
MLflow · Deployment & Serving
An open-source MLOps platform covering the full lifecycle: experiment tracking, model registry, and deployment management.
Free Tutorial
Intermediate
Made With ML Course
Goku Mohandas · Deployment & Serving
A production-oriented ML course covering the full engineering loop: features, training, deployment, and monitoring.
Official Course
Intermediate
Full Stack Deep Learning
Full Stack Deep Learning · Deployment & Serving
A university-backed full-stack deep learning course spanning the whole engineering pipeline from data to deployment.
Official Docs
Intermediate
Weights & Biases Documentation
W&B · Deployment & Serving
Docs for the popular experiment tracking platform: log metrics, compare runs, and manage datasets, with a generous free tier for individuals.
Official Docs
Intermediate
Hugging Face Inference Providers Documentation
Hugging Face · Deployment & Serving
Hugging Face's unified inference API docs — one endpoint to call hosted models from multiple providers.
Open Source Project
Intermediate
AI Engineer Roadmap Repository
dswh · Deployment & Serving
A three-stage learning roadmap repository from LLM API basics to LLMOps, with a long list of project ideas.
No matching resources. Try different keywords or relax the filters.