Intel plans cheaper air-cooled ai chip for inference

Intel will ship a new graphics processing unit designed for AI inference tasks by the end of this year. The chip uses lower-cost memory and air cooling to undercut rivals Nvidia and AMD.

The US chipmaker unveiled the Crescent Island GPU in October as part of efforts to regain ground in the AI semiconductor market. Kevork Kechichian, who leads Intel’s data center group, said the company is “starting with the basics” and will not target the model training segment after its earlier Gaudi product saw weak sales and a successor was cancelled last year.

관련 기사

Google has introduced two new Tensor Processing Units, the TPU 8t for training and TPU 8i for inference, targeting what the company calls the agentic era of AI. These eighth-generation chips follow the Ironwood TPU from 2025 and promise faster, more efficient AI development. The hardware aims to cut training times for large models from months to weeks.

AI에 의해 보고됨

Advanced Micro Devices posted first-quarter results that topped expectations, with revenue climbing 38 percent on robust server chip sales tied to artificial intelligence.

Nebius Group continues to see strong interest in its AI computing services.

AI에 의해 보고됨

Nvidia has described AI as a five-layer industrial system. CEO Jensen detailed the AI layered stack and hinted at the company's next moves. The firm eyes expansion across technology layers, akin to Amazon beyond cloud services.

이 웹사이트는 쿠키를 사용합니다

사이트를 개선하기 위해 분석을 위한 쿠키를 사용합니다. 자세한 내용은 개인정보 보호 정책을 읽으세요.
거부