Inferact and Google Cloud partner to make TPUs first-class in vLLM
Original title@googlecloud and Inferact are announcing today a partnership to make TPU a first-class citizen in @vllm_project.
AISummary
Inferact and Google Cloud announce a partnership to make Google TPUs a first-class platform in the vLLM open-source project.
The collaboration targets production serving features, optimized kernels, a native PyTorch path via TorchTPU, and day-0 support for frontier model releases.
A community program will offer shared TPU capacity and review and design help from vLLM core maintainers, with all outputs released as open source.
Source: Inferact · x.comPublished · added here