Lead story
Models & availability
Latest
← Feed
Copy✕ Close copy menu
OpenAI and Broadcom unveil LLM-optimized inference chip
OpenAI and Broadcom introduce a custom AI chip named Jalapeño, built for LLM inference to improve performance, efficiency, and scale across AI systems.
From the source
OpenAI and Broadcom introduce Jalapeño, a custom AI chip built for LLM inference to improve performance, efficiency, and scale across AI systems.
openai.com
Visit source ↗openai.com
- Announced
- 24 Jun 2026 06:00 UTC
- Detected
- 03 Aug 2026 21:11 UTC (+40d after)