OpenAI has introduced its first in-house AI chip, Jalapeño, designed to power next-generation AI models.
The custom chip is built to deliver faster large language model (LLM) inference, improving AI response times and efficiency.
Jalapeño is specifically engineered for AI inference, helping reduce latency while boosting performance for advanced AI applications.
By developing its own silicon, OpenAI aims to reduce dependence on third-party hardware and improve the cost efficiency of running AI models.
The chip is expected to support OpenAI’s next generation of AI models and large-scale infrastructure.
The launch marks OpenAI’s move into custom AI hardware, joining other tech giants investing in specialized AI chips.