{"type":"analysis","id":"analysis:research-google-s-tpus-are-becoming-a-serving-layer-outside-google-but-the-proof-so-far","slug":"research-google-s-tpus-are-becoming-a-serving-layer-outside-google-but-the-proof-so-far","title":"Google's TPUs are becoming a serving layer outside Google, but the proof so far is benchmarks and vendor claims, not audited production data","description":"SemiAnalysis's InferenceX preview puts Ironwood ahead of B200/B300 on FP8 cost per token. Google has open-sourced native PyTorch, vLLM and SGLang backends, and Meta and Anthropic are external users. Still missing: independent production latency, availability and FP4-era comparisons.","published_at":"2026-10-23T02:00:00.000Z","updated_at":"2026-10-23T02:00:00.000Z","record_date":"2026-10-23","topics":["google","anthropic","benchmarks","research"],"source_urls":["https://inferencex.semianalysis.com/blog/tpu-inferencex-full-steam","https://inferencex.semianalysis.com/about","https://cloud.google.com/blog/topics/ai-infrastructure/torchtpu-is-now-open-source-run-native-pytorch-on-tpus","https://developers.googleblog.com/announcing-new-vllm-and-sglang-inference-engines-on-tpu/","https://anthropic.com/news/expanding-our-use-of-google-cloud-tpus-and-services","https://finance.yahoo.com/news/google-signs-multibillion-dollar-ai-232844608.html","https://www.networkworld.com/article/4173075/google-opens-tpus-to-enterprises-beyond-its-own-cloud-via-blackstone-jv.html"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-google-s-tpus-are-becoming-a-serving-layer-outside-google-but-the-proof-so-far/","markdown":"https://newruntime.com/analysis/research-google-s-tpus-are-becoming-a-serving-layer-outside-google-but-the-proof-so-far.md","json":"https://newruntime.com/analysis/research-google-s-tpus-are-becoming-a-serving-layer-outside-google-but-the-proof-so-far.json"},"author":{"role":"author","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:1a18726c-1e4f-40bc-8c7d-98aebe81d22a","authorial_article_id":"1a18726c-1e4f-40bc-8c7d-98aebe81d22a"},"next_reads":[{"type":"topic","path":"/topics/google/","url":"https://newruntime.com/topics/google/","title":"Google","reason":"Explore the google topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/google.md","json_url":"https://newruntime.com/topics/google.json"},{"type":"topic","path":"/topics/anthropic/","url":"https://newruntime.com/topics/anthropic/","title":"Anthropic","reason":"Explore the anthropic topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/anthropic.md","json_url":"https://newruntime.com/topics/anthropic.json"},{"type":"topic","path":"/topics/benchmarks/","url":"https://newruntime.com/topics/benchmarks/","title":"Benchmarks","reason":"Explore the benchmarks topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/benchmarks.md","json_url":"https://newruntime.com/topics/benchmarks.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}