Google Submits First TPUv7 AgentX Benchmark, Served with vLLM

1 reports 1 reporting sources 1 day agoNew

Understand the event

AI overview

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.

Generated by AI from reports · Updated 1 day ago

Latest development10/16 08:48 (UTC+8)

vLLM Reports First TPUv7 Submission to AgentX, Served with vLLM vLLM · X

Report timeline

Follow the reports to explore different sides of the event.

10/16

08:48
vLLM · X
vLLM Reports First TPUv7 Submission to AgentX, Served with vLLM
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. https://t.co/Ea730oFhrd

Event heat trend

可比范围当前: 5
Peak within comparable coverage: 1010/16 09:00 (UTC+8)
近 24 小时变化: -49%

Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.

Keep reading

Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation Pipeline