212 views · 3 likes · 0 reposts (at collection)
vLLM Reports First TPUv7 Submission to AgentX, Served with vLLM
- Who
- What
- submitted its first TPUv7 submission to the AgentX benchmark, served with vLLM
What happened
We’re excited to see the first TPUv7 submission to AgentX, served with vLLM. Thanks to the @Google TPU, @RedHat_AI, and @inferact folks who put in the work to get it running, and we’re looking forward to more models landing on TPU through AgentX.
Links in the post: 1The story so far
Google submitted its first TPUv7 benchmark to AgentX, with vLLM serving the workload, according to vLLM. The submission was reported to deliver 1.42x the performance per dollar of GB300 NVL72 FP4 on an external, non-Google workload cost basis; that figure is a claim accompanying the submission. vLLM credited Google TPU, Red Hat AI and inferact contributors with getting the setup running.
Keep reading
Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation PipelineTrending now
- 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
- 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
- 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
- 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-17