Back to Featured
Google Developers Blog2026-10-20 00:0028 days ago

Google released native TorchTPU inference engines for vLLM and SGLang

Announcing New vLLM and SGLang Inference Engines on TPU

AI Briefing

In a PyTorch-related announcement, Google introduces native PyTorch inference engines for vLLM and SGLang based on TorchTPU, developed with Inferact and RadixArk respectively, allowing developers to deploy models on TPUs using familiar PyTorch tools.

Also reported by 2 other sources

Source: Google Developers Blog · developers.googleblog.com

Event follow-up1

View all event coverage

Finished reading the news? Let’s talk about your business.

Leave your contact details, and I’ll get in touch with you personally.

WECHAT

Add me on WeChat

Press and hold or select the WeChat ID below to copy it.