vLLM

Google TorchTPU: Native PyTorch for Cloud TPUs Goes Open Source

Google TorchTPU: Native PyTorch for Cloud TPUs Goes Open Source

Google announced TorchTPU at PyTorch Conference 2026, open sourcing native PyTorch support for Cloud TPUs and integrating it across vLLM, SGLang, llm-d, Ray, and Hugging Face. The release is less a hardware story than a developer ecosystem play, designed to make TPUs the path of least resistance for AI teams already building on PyTorch. LiteRT also joins the PyTorch Ecosystem, closing the training-to-edge deployment gap.

Google TorchTPU: Native PyTorch for Cloud TPUs Goes Open Source Read More »

VMware Explore 2026: Private AI Cloud Expands Model Choice and Agentic Security

VMware Explore 2026: Private AI Cloud Expands Model Choice and Agentic Security

At VMware Explore 2026, Broadcom extended its Private AI Cloud strategy with an expanded validated model catalog spanning five vendors and more than 150 open-source models via vLLM. The company also announced planned Agentic Zero Trust capabilities for vDefend and Avi Load Balancer designed to discover shadow AI and secure agent transactions. ECI Research examines the architecture, the governance gaps, and what enterprise buyers should evaluate before committing.

VMware Explore 2026: Private AI Cloud Expands Model Choice and Agentic Security Read More »