Engineering
-
Oct 14, 2025
Join Us in Revitalizing the Docker Model Runner Community!
Docker Model Runner is GA, now in all Docker versions with Vulkan support for nearly any GPU. Star, fork, and contribute in our unified repo.
Eric CurtinRead now
-
Oct 9, 2025
LoRA Explained: Faster, More Efficient Fine-Tuning with Docker
LoRA is a method that freezes a base model and adds trainable adapters to teach pre-trained models new behaviors, without overwriting their existing knowledge.
Ignasi Lopez LunaRead now
-
Oct 8, 2025
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.
Eric CurtinRead now
-
Oct 6, 2025
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,…
Eric CurtinRead now
-
Oct 6, 2025
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.
Oleg SelajevRead now
-
Oct 6, 2025
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
Eric CurtinRead now
-
Oct 2, 2025
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.
Ignasi Lopez LunaRead now
-
Sep 26, 2025
The Trust Paradox: When Your AI Gets Catfished
Learn how MCP prompt-injection exploits trusted tools—and how to defend with context isolation, AI behavior checks, and human-in-the-loop review.
Saurabh DavalaandSundeep GottipatiRead now