{
  "id": 15739489,
  "title": "IBM-backed llm-d framework adds controls for running AI models in-house",
  "url": "https://urgent.news/2026/10/20/ibm-backed-llm-d-framework-adds-controls-for-running-ai-models-in",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-20T12:00:23.000Z",
  "source": {
    "name": "SiliconANGLE",
    "slug": "siliconangle",
    "url": "https://siliconangle.com/2026/10/20/ibm-backed-llm-d-framework-adds-controls-for-running-ai-models-in-house/"
  },
  "original_language": "en",
  "account": null,
  "summary": "IBM has released version 1.0 of the llm-d framework, an open-source distributed artificial intelligence inference framework that adds operational controls for running AI models in-house. The release, announced ahead of the PyTorch Conference North America, focuses on managing competing workloads, maintaining service during upgrades, and improving hardware efficiency. The framework, built for Kubernetes, coordinates model serving across computing infrastructure and aims to help enterprises reduce dependence on a single model provider, cloud, or hardware platform. IBM, Red Hat, and Google are the lead maintainers of the project, which was co-founded with CoreWeave Inc. and Nvidia Corp. Other contributors include AMD, Cisco, Hugging Face, Intel, and Mistral AI SAS. The release adds support for quality of service across multiple tenants, zero-downtime operations, and serving patterns tailored to AI agents, with flow controls and prioritization designed to prevent bursts of agent activity from overwhelming services that require fast responses.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}