{"slug": "radixark-helps-bring-sglang-to-google-tpus-as-meta-runs-it-in-production", "title": "RadixArk helps bring SGLang to Google TPUs as Meta runs it in production", "summary": "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.", "body_md": "# RadixArk helps bring SGLang to Google TPUs as Meta runs it in production\n\n**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.**\n\n        By [RuntimeWire Staff](https://runtimewire.com/author/runtimewire-staff)\n        · Published \n\nPrimary source: [Google Developers Blog](https://developers.googleblog.com/announcing-new-vllm-and-sglang-inference-engines-on-tpu/)\n\n## Why it matters\n\nGoogle'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.\n\nMeta 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.…\n\nWhen 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.", "url": "https://wpnews.pro/news/radixark-helps-bring-sglang-to-google-tpus-as-meta-runs-it-in-production", "canonical_source": "https://runtimewire.com/article/meta-runs-sglang-google-tpu-radixark", "published_at": "2026-10-22 10:14:22+00:00", "updated_at": "2026-10-22 13:40:08.939316+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-chips", "large-language-models", "ai-tools"], "entities": ["Google", "Meta", "RadixArk", "SGLang-TorchTPU", "TorchTPU", "PyTorch", "Ying Sheng", "Nvidia"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/radixark-helps-bring-sglang-to-google-tpus-as-meta-runs-it-in-production", "markdown": "https://wpnews.pro/news/radixark-helps-bring-sglang-to-google-tpus-as-meta-runs-it-in-production.md", "text": "https://wpnews.pro/news/radixark-helps-bring-sglang-to-google-tpus-as-meta-runs-it-in-production.txt", "jsonld": "https://wpnews.pro/news/radixark-helps-bring-sglang-to-google-tpus-as-meta-runs-it-in-production.jsonld"}}