Trending storyDeveloping
Google releases native TorchTPU inference backends for vLLM and SGLang
1 report1 sourceupdated 1 hour ago
What happened
AI digest
On October 20, 2026, Google released native PyTorch inference backends for vLLM and SGLang built on TorchTPU, according to AI HOT. The vLLM backend was developed with Inferact and the SGLang backend with RadixArk. The report covers only the releases themselves; it gives no version numbers, performance figures or deployment details.
Written by AI from the coverage · updated 1 hour ago
Coverage
Follow the reports to see the story from different sides.
Oct 20
- AI HOT · ProductsGoogle 发布基于 TorchTPU 的 vLLM 与 SGLang 原生推理引擎
Google 发布基于 TorchTPU 的 vLLM 与 SGLang 原生 PyTorch 推理后端，分别与 Inferact 和 RadixArk 联合开发。
Heat over time
Not enough continuous observations to draw a trend yet.