ULTRAULTRA MAGA Price

According to Beating AI news, OpenAI has announced the latest test results of its self-developed AI inference chip, Jalapeño. The chip outperformed Nvidia's GB200 and GB300 superchips in the InferenceX benchmark tests, achieving 1.5 to 1.9 times the AI workload per watt on models such as GPT-OSS 120B, DeepSeek R1, and Kimi K2.5 1T, while reducing end-to-end latency by 1.7 to 3.6 times. OpenAI stated that Jalapeño utilizes an ASIC architecture developed in collaboration with Broadcom, specifically designed for AI inference, aiming to enhance throughput while reducing latency. The company plans to initiate small-scale deployment by the end of this year, expand production by 2027, and continue developing second and third-generation chips. However, the company emphasized that it will not completely replace chips from partners like Nvidia.

According to Beating AI News, OpenAI has announced the latest test results for its self-developed AI inference chip, Jalapeño. The chip outperformed Nvidia's GB200 and GB300 superchips in the InferenceX benchmark tests, achieving 1.5 to 1.9 times the AI workload per watt on models such as GPT-OSS 120B, DeepSeek R1, and Kimi K2.5 1T, with end-to-end latency reduced by 1.7 to 3.6 times. OpenAI stated that Jalapeño utilizes an ASIC architecture developed in collaboration with Broadcom, specifically designed for AI inference, aiming to enhance throughput while reducing latency. The company plans a small-scale deployment by the end of this year, with plans to scale up production by 2027 and continue developing second and third-generation chips. However, the company emphasized that it will not completely replace chips from partners like Nvidia.

Nvidia CEO Huang Renxun said that Nvidia will launch the Blackwell Ultra AI chip in 2025. He also stated that the next generation AI platform will be named Rubin, and it will use HBM4 memory.