Docker Blog
-
From the Captain’s Chair: Pradumna Saraf
In this edition of From the Captain’s Chair, we’re interviewing Pradumna Saraf. Hear about how he was producing Docker content long before he became a Captain, his love of open source, and what he enjoys outside of tech.
Read now
-
Unlocking Local AI on Any GPU: Docker Model Runner Now with Vulkan Support
Run local LLMs on more GPUs with Docker Model Runner. New Vulkan support accelerates AMD, Intel, and integrated GPUs—auto-detects hardware with CPU fallback.
Read now
-
Powered by Docker: How Open Source Genius Cut Entropy Debt with Docker MCP Toolkit and Claude Desktop
Open Source Genius built a local, secure file automation agent with Docker MCP Toolkit + Claude Desktop—set up in under 1 hour, saving ~2 hours/week.
Read now
-
IBM Granite 4.0 Models Now Available on Docker Hub
Developers can now discover and run IBM’s latest open-source Granite 4.0 language models from the Docker Hub model catalog, and start building in minutes with Docker Model Runner. Granite 4.0 pairs strong, enterprise-ready performance with a lightweight footprint, so you can prototype locally and scale confidently. The Granite 4.0 family is designed for speed, flexibility,…
Read now
-
Docker at AI Engineer Paris: Build and Secure AI Agents with Docker
Highlights from AI Engineer Paris: how Docker’s MCP Toolkit & Catalog and cagent help teams build, run, and secure AI agents—from local dev to production.
Read now
-
Llama.cpp Gets an Upgrade: Resumable Model Downloads
New: resumable GGUF downloads in llama.cpp. Learn how Docker Model Runner makes models versioned, shareable, and OCI-native for seamless dev-to-prod
Read now
-
From Shell Scripts to Science Agents: How AI Agents Are Transforming Research Workflows
See how AI science agents automate literature search, ADMET, and analysis in containerized, reproducible workflows—from laptop to cloud—with Docker.
Read now
-
Fine-Tuning Local Models with Docker Offload and Unsloth
Learn how to fine-tune models locally with Docker Offload and Unsloth and how smaller models can become practical assistants for real-world problems.
Read now