GoKawiilOpenAI pairs its Jalapeño ASIC with AMD EPYC Turin, not Nvidia Vera
OpenAI is deploying its new Jalapeño AI chip in racks alongside AMD's EPYC Turin CPUs, each configured with 1.5TB of memory, rather than Nvidia's newer Vera processor. Richard Ho, OpenAI's VP and Head of Hardware, told Tom's Hardware that Turin was chosen for pragmatic reasons, calling Vera 'a little bit behind' in maturity and noting partners already had experience with AMD's chip.
GoKawiil's interpretation of the reporting above, not reported fact.
The choice suggests OpenAI prioritized proven, lower-risk infrastructure over Nvidia's latest agentic-focused CPU despite the companies' close partnership, which could signal that Vera isn't yet ready for large-scale production deployment. It also indicates that claims about agentic CPUs like Vera and Arm's AGI outperforming x86 chips may not yet be translating into real-world hyperscaler adoption, since those performance claims remain based on internal estimates rather than independent benchmarks.
- OpenAI's Jalapeño ASIC runs with AMD EPYC Turin hosts featuring 1.5TB memory each, not Nvidia Vera.
- OpenAI's hardware chief called Vera less mature and said Turin reduced deployment risk and cost.
- Arm's claims about agentic CPU advantages over x86 remain based on internal estimates, not verified benchmarks.
Source: tomshardware.com — Jake Roach, 2026-10-02
Published there as: “OpenAI’s Jalapeño ASICs are deployed alongside AMD EPYC ‘Turin’ CPUs as hosts, not Nvidia's Vera”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.