Google Cloud and Inferact partner to expand TPU support in vLLM

Inferact announced a partnership with Google Cloud to make TPU a first-class platform in vLLM, an engine for serving AI models. The shared roadmap includes production-serving features, optimized kernels and a native PyTorch path through TorchTPU. The teams are working toward day-zero support for frontier model releases. Inferact also announced a community program offering open-source contributors shared TPU capacity, plus review and design help from its core vLLM maintainers. It says everything the collaboration produces will be open source.