What if your local machine could run high-throughput LLMs, multimodal models, or even fine-tune small AI models with GPU acceleration? In this new episode of AI Guide to the Galaxy, Oleg sits down with Eric from the Docker Model Runner team to explore how the project is evolving to make all of that possible. 🎙️ In this episode: - How Docker Model Runner is expanding support for engines like VLLM and NVIDIA NIMs - Running models on AMD GPUs and integrated graphics via Vulkan - Using multimodal m

Manage AI models like container images? Yep, that's a thing now. At #GoogleCloudNext, Docker DevRel Michael Irwin gives us a sneak peek at the new Docker Model Runner—a tool that lets you manage and run GenAI models just like you already do with containers. ✅ Pull models from Docker Hub ✅ Use OpenAI-compatible endpoints ✅ Add models to docker-compose.yml ✅ Run them natively on your machine #Docker #GenAI #AItools #DevLife #GoogleCloudNext #OpenSource | Docker