OpenAI announced that its self-developed AI chip, Jalapeño, can achieve inference performance up to 1.9 times that of NVIDIA Blackwell. NVIDIA will release its earnings report after hours.
OpenAI stated that its Jalapeño chip, developed in collaboration with Broadcom, can achieve up to 1.9 times the AI inference throughput of NVIDIA Blackwell architecture systems, reduce end-to-end latency by 1.7 to 3.6 times, and accelerate ultra-low latency interactive inference by 2.1 to 4.1 times. The chip is expected to begin deployment in late 2026 and achieve mass production in 2027. This announcement comes just before NVIDIA's Q2 earnings report. Although OpenAI's chip is not yet widely deployed and primarily targets inference rather than training, analysts have mixed views on its potential impact.
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
BitDATA Exchange Token BDT: Multi-Entity and Token Analysis, and Scam Alert
-
2
BCUG Coin Analysis: The Current State of Blockchain Cuties Universe Governance Token and Market Liquidity
-
3
AGGL Coin Value Analysis: Extremely Low Market Activity, Questionable Investment Prospects
-
4
An Analysis of the Current State of Virtual Currency Regulation and Trading Risks in Mainland China
-
5
CHP Coin Trading Guide: Understanding the Uses and Acquisition Methods of CoinPoker Tokens
-
6
BCB Coin: Analyzing its Value and Investment Potential
-
7
Bitcoin Contract Arbitrage: Yield Analysis and Potential Risks
-
8
SIGIL Coin: Multi-Entity Analysis and Trading Status
-
9
Virtual Currency Exchange Platforms and Software: Mainstream Choices and Feature Analysis
-
10
PROPS (Propbase) Buying and Trading Guide: Exchange Listings and Market Status Analysis
Markets Today
Recommended Reading












