NVIDIA touts Vera CPU for higher AI agent throughput and power efficiency
Growing use of AI agents is increasing demand for data center processors that can handle more execution steps without raising power consumption. NVIDIA says its Vera CPU is designed to improve both agent speed and capacity per watt in AI factory deployments.
Highlights
- NVIDIA claims Vera CPU delivers 1.6 times more agents per watt than the fastest x86 processor and twice the agent speed of the most energy-efficient x86 CPU in 100-megawatt data center comparisons.
- Perplexity reports Vera executes agentic coding tasks 1.5 times faster than traditional CPUs and plans deployment in an upcoming production system.
- DeepInfra states Vera reaches up to 2.2 times the speed of the best x86 processor for its production agent orchestration workload.
Benchmark claims and early deployment plans
NVIDIA Newsroom says the chip is aimed at workloads in which AI agents move repeatedly between GPU-based reasoning and CPU-based execution for tasks such as database queries, code testing and action-taking. The company says operators of power-constrained AI factories need infrastructure that can support more agents at the same time without extending wait times for each task.NVIDIA says that, in a 100-megawatt data center comparison, a single Vera CPU outperforms both the fastest x86 CPU and the most energy-efficient x86 CPU. According to the company, Vera delivers 1.6 times more agents per watt than the fastest x86 processor while also providing industry-leading agent speed, and it delivers twice the agent speed of the most energy-efficient x86 CPU with what it describes as leading energy efficiency.
The company also cites production-style tests from early adopters. Perplexity says it runs agentic coding tasks 1.5 times faster with Vera than on traditional CPUs and plans to deploy the processor in an upcoming production system, while DeepInfra says Vera reaches up to 2.2 times the speed of the best x86 processor on agentic orchestration for its production agent workload.
In our earlier article on the strain facing U.S. AI data center expansion, we noted that a growing share of projects is being delayed or scaled back as rising interest rates and inflation make financing harder to secure. We also highlighted how power-grid limits, local opposition, and cost overruns are adding pressure on developers to deliver new capacity on time and on budget—an issue that directly frames today’s push for more energy-efficient AI compute in data centers.
-
Afghanistan
-
Albania
-
Algeria
-
Angola
-
Argentina
-
Armenia
-
Australia
-
Austria
-
Azerbaijan
-
Bahamas
-
Bahrain
-
Bangladesh
-
Belarus
-
Belgium
-
Bolivia
-
Botswana
-
Brazil
-
Brunei
-
Bulgaria
-
Cambodia
-
Cameroon
-
Canada
-
Chile
-
China
-
Colombia
-
Congo
-
Costa Rica
-
Cote d'Ivoire
-
Croatia
-
Cuba
-
Cyprus
-
Czechia
-
DR Congo
-
Denmark
-
Dominican Republic
-
Ecuador
-
Egypt
-
El Salvador
-
Estonia
-
Eswatini
-
Ethiopia
-
Finland
-
France
-
Georgia
-
Germany
-
Ghana
-
Greece
-
Haiti
-
Hong Kong
-
Hungary
-
India
-
Indonesia
-
Iran, Islamic republic
-
Iraq
-
Ireland
-
Israel
-
Italy
-
Jamaica
-
Japan
-
Jordan
-
Kazakhstan
-
Kenya
-
Korea
-
Kuwait
-
Kyrgyzstan
-
Laos
-
Latvia
-
Lebanon
-
Lesotho
-
Libya
-
Lithuania
-
Luxembourg
-
Madagascar
-
Malaysia
-
Malta
-
Mauritius
-
Mexico
-
Moldova
-
Mongolia
-
Montenegro
-
Morocco
-
Mozambique
-
Myanmar
-
Namibia
-
Nepal
-
Netherlands
-
New Zealand
-
Nigeria
-
North Macedonia
-
Norway
-
Oman
-
Pakistan
-
Palestine
-
Panama
-
Papua New Guinea
-
Paraguay
-
Peru
-
Philippines
-
Poland
-
Portugal
-
Puerto Rico
-
Qatar
-
Reunion
-
Romania
-
Rwanda
-
Saudi Arabia
-
Serbia
-
Singapore
-
Slovakia
-
Slovenia
-
Somalia
-
South Africa
-
Spain
-
Sri Lanka
-
Sweden
-
Switzerland
-
Syria
-
Taiwan
-
Tajikistan
-
Tanzania
-
Thailand
-
Trinidad and Tobago
-
Tunisia
-
Turkey
-
UAE
-
Uganda
-
Ukraine
-
United Kingdom
-
United States
-
Uruguay
-
Uzbekistan
-
Venezuela
-
Vietnam
-
Yemen
-
Zambia
-
Zimbabwe
- Forex
- Crypto
