analiza aiqbench
OpenAI's custom Jalapeño chip demonstrates a significant architectural breakthrough by unifying high throughput and low latency within a single design, eliminating traditional hardware trade-offs. By integrating silicon with memory and networking specifically for modern language models, the chip reduces data movement bottlenecks to deliver up to 1.9x more work per watt across diverse open-source models. This holistic stack optimization sets a new benchmark for efficient AI inference, directly addressing the industry's need to scale capable agents without prohibitive energy costs.
OpenAI’s Jalapeño chip boosts AI speed and cuts power use

OpenAI’s Jalapeño inference chip delivers industry-leading speed and efficiency, serving up to 1.9x more AI work per watt.
OpenAI reports its first custom inference chip, Jalapeño, can serve more AI work per unit of power while also returning responses more quickly. Jalapeño delivers both higher throughput and lower latency with one architecture, a feature often requiring tradeoffs in existing hardware systems. The chip achieves this efficiency across GPT‑OSS 120B, DeepSeek R1, and Kimi K2.5 1T, delivering 1.5 to 1.9 times more AI work per watt at peak throughput and 1.7 to 3.6 times lower end-to-end latency than comparison systems. For highly interactive workloads, it delivered 2.1 to 4.1 times higher performance. OpenAI…
Extras afișat conform termenilor RSS ai publicației · 94 cuvinte · textul integral și figurile sunt pe site-ul publicației
Subiecte conexe

[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026

Forbes Asia 100 To Watch 2026
forbes.com · 24 aug. 2026
The hard physics and complex economics of AI’s insatiable hunger for power
SiliconANGLE · 11 sept. 2026

Nvidia’s new financial strategy does not compute
The Verge · 19 aug. 2026