semantic-scholar
Semantic Scholar1 events on 2025-09-30role: thematic30d fetch windowcadence: on demandaccess: keyless
Extracts: paper title, abstract snippet · metadata or bounded excerpt
Retention: D1 event history with canonical source link and deduplication metadata.
Access basis: Public endpoint; no project credential required.
Last ingested: 2026-08-12 · run status: on demand
Archive source — full history has value. Use pagination to browse older records.
Query: ai datacenter power cooling efficiency Authors: Jovan Stojkovic, Chaojie Zhang, Íñigo Goiri, Ricardo Bianchini Citations: 6 The rapid rise of large language models (LLMs) has been driving an enormous demand for AI inference infrastructure, mainly powered by high-end GPUs.