Groq 3 LPX AI racks, following NVIDIA's $20 billion acquisition of Groq's assets, are now in full production and will be deployed at Nebius later this year.
NVIDIA Senior Director Dion Harris informed reporters that the Groq 3 LPX rack has entered full production and will be deployed later this year alongside NVIDIA's Vera CPU and Rubin GPU in neocloud Nebius. This rack marks the commercialization of Groq's asset technology, which NVIDIA acquired last December for $20 billion, its largest recorded transaction. Each liquid-cooled rack encapsulates 256 Groq chips, and NVIDIA states it can deliver 3,400 tokens per second, surpassing the 750 tokens of the "ultrafast" mode supported by OpenAI Cerebras.
No AI analysis yet. Tap the "AI Analysis" button above to generate one now.
Source:Yahoo财经 · 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
Analysis of Virtual Currency Trading Platforms and Regulatory Status in Mainland China
-
2
Netherlands' Central Bank Moves Gold Out of New York, Norway's $2.4 Trillion Oil Fund Plans to Cut US Treasury Holdings
-
3
Huawei will stand trial in Brooklyn, USA, where a jury will decide whether its rise was built on crime.
-
4
IVN Token: An Analysis of Investin Protocol's Token Status and Market Activity
-
5
ORN Trading Guide: Buying, Selling, and Platforms for Orion Protocol Tokens
-
6
Ethereum founder Vitalik Buterin praised Poseidon hash and STARKs technology on X, stating that they offer immense value for Ethereum privacy protocols and ultra-fast general computation.
-
7
ITC (IoT Chain) Analysis: Current Status and Prospects of an IoT Blockchain Project
-
8
Bitcoin Price Today: Real-time Quotes and Market Trend Analysis (September 7, 2026)
-
9
CBETH Token Trading Guide: How to Buy and Sell on Centralized and Decentralized Platforms?
-
10
Moody's Ratings Report: Chinese AI giants are "punching above their weight" in the computing power race, with lower domestic costs and state support enabling them to achieve significantly more computing power per dollar than their US counterparts.
Markets Today
Recommended Reading








