RadixArk helps bring SGLang to Google TPUs as Meta runs it in production

Meta said on October 20th that it is running SGLang-TorchTPU in production, bringing Google's custom AI chips into a major PyTorch shop. RadixArk, the startup co-founded by Ying Sheng, worked with Google and Meta on the engine, and Google says it co-developed TorchTPU with Meta's PyTorch team, according to the Google Developers Blog. The deployment matters because Google's TPU challenge to Nvidia depends on software as much as silicon.

RadixArk helps bring SGLang to Google TPUs as Meta runs it in production Google says it co-developed TorchTPU with Meta's PyTorch team; RadixArk worked with Google and Meta on SGLang-TorchTPU, which Meta says is in production. By RuntimeWire Staff https://runtimewire.com/author/runtimewire-staff · Published Primary source: Google Developers Blog https://developers.googleblog.com/announcing-new-vllm-and-sglang-inference-engines-on-tpu/ Why it matters Google's TPU challenge to Nvidia depends on software as much as silicon. Meta's deployment puts Google's PyTorch-native approach into production at a major PyTorch shop. Meta said on October 20th that it is running SGLang-TorchTPU https://github.com/sgl-project/sglang-torchtpu?ref=runtimewire in production, putting Google's https://google.com/?ref=runtimewire custom AI chips to work at a major PyTorch shop. RadixArk, the startup co-founded by Ying Sheng https://sites.google.com/view/yingsheng/home?ref=runtimewire , worked with Google and Meta on the engine.… When you purchase through links in our articles, we may earn a small commission https://runtimewire.com/affiliate-monetization-standards . This doesn’t affect our editorial independence.