Docker Hub
-
Jan 15, 2026
OpenCode with Docker Model Runner for Private AI Coding
Configure OpenCode to use Docker Model Runner for a private, cost-aware coding assistant. Run models locally via an OpenAI-compatible API with full control.
Ignasi Lopez LunaRead now
-
Jan 14, 2026
Safer Docker Hub Pulls via a Sonatype-Protected Proxy
Why a “protected repo”? Modern teams depend on public container images, yet most environments lack a single, auditable control point for what gets pulled and when. This often leads to three operational challenges: Inconsistent or improvised base images that drift across teams and pipelines. Exposure to new CVEs when tags remain unchanged but upstream content…
Anna ChernyshovaandAndrés PérezRead now
-
Dec 5, 2025
Announcing vLLM v0.12.0, Ministral 3 and DeepSeek-V3.2 for Docker Model Runner
Run Ministral 3 and DeepSeek-V3.2 on Docker Model Runner with vLLM 0.12. Test-drive the latest open-weights models as soon as they’re released.
Eric CurtinRead now
-
Dec 3, 2025
Securing the Docker MCP Catalog: Commit Pinning, Agentic Auditing, and Publisher Trust Levels
Learn how we’re enhancing trust in the MCP ecosystem with commit planning, AI-audited updates, and publisher trust levels within the Docker MCP catalog.
Jacob HowardandMat WilsonRead now
-
Nov 20, 2025
Docker Model Runner Integrates vLLM for High-Throughput Inference
New: vLLM in Docker Model Runner. High-throughput inference for safetensors models with auto engine routing for NVIDIA GPUs using Docker.
Dorin Geman,Eric Curtin,andIgnasi Lopez LunaRead now
-
Oct 24, 2025
Your Org, Your Tools: Building a Custom MCP Catalog
Fork Docker’s MCP Catalog, host images in your registry, publish a private catalog, and expose servers via MCP Gateway to run a controlled MCP environment.
Mike ColemanRead 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 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