NVIDIAGroq 3 LPX Enters Full Production, Expands Vera Rubin NVL72 System, Delivering 3,400 Tokens/Second for Agentic AI, 4x Faster Than Competitors
NVIDIAGroq 3 LPX has entered full production, and the Vera Rubin NVL72 system has been expanded, aiming to provide fast token generation for agentic AI systems. In the Gemma 4 31B benchmark, Groq 3 LPX achieved 3400 output tokens per second in 100,000-token long-context use cases, which is 4 times faster than the closest alternative platform. Nebius is the first AI cloud to adopt Groq 3 LPX, SpaceXAI will use NVIDIAVera CPU, and CoreWeave has also deployed Spectrum-X Multiplane.
Source:NVIDIA官方博客 · Source Link
Disclaimer: This content reflects only the author’s personal views and does not constitute any investment or financial advice. If you discover any content that violates regulations,Click to Report
24H Trending
-
1
Crypto Adoption Reaches 25% in Europe's Four Largest Economies: Banks Accelerate Layout Under MiCA Push
-
2
USDT and Digital Currency Exchange Selection Guide: Global Compliance and Reliability Considerations
-
3
Dollar Rises, U.S. Treasury Yields Fall
-
4
AI scammers are scouring obituaries to target widows, with one losing $7,000 after being told her late husband evaded taxes
-
5
T. Rowe Price to acquire fixed income fund manager F/m Investments, which manages $19bn in assets
-
6
Gemini partners with Apex Fintech Solutions to expand regulated crypto prediction markets
-
7
Retired Lineman Made Costly Error by Accepting $310,000 Pension Buyout Check Personally, Triggering 20% Federal Withholding and Potential Tax Penalties
-
8
Ozon, Russia's second-largest online retailer, saw its shares drop by 12% after its warehouse was hit by a Ukrainian drone attack.
-
9
Bybit to support STABLE (STABLE) network upgrade on Aug 26, 2026; deposits and withdrawals to be temporarily suspended.
-
10
How to Choose a Reliable Cryptocurrency Exchange Platform? A Guide to Evaluating Mainstream Platforms
Markets Today
Recommended Reading





