Google’s TPUs for AI workloads now run in Meta's data centers
Google’s tensor processing units (TPUs) — its custom AI chips — now serve AI in production at Meta (creator of the widely used PyTorch AI framework) through a new PyTorch-native version of the SGLang inference engine, announced on Google’s developer blog. A matching version of vLLM, another widely used inference engine, was also announced as open source.
Previously, both engines used Google’s own JAX AI framework to run on TPUs. The new versions allow the hardware to be a native option for PyTorch, mostly without rewriting.
Go deeper with TH Premium: AI and data centers
America’s AI chip rules keep changing — and the rest of the world is paying the price
GTC 2026: Ian Buck press Q&A transcript — VP of Hyperscale and HPC speaks out on shelving CPX and shipping LPU decode this year
Demand for data center CPUs has surged, and AI agents are responsible
“SGLang-TorchTPU is running in production at Meta today” after “a close three-way …
You're reading a preview. The full article is published by Tom's Hardware on their website.
Read the full story on Tom's Hardware
