semantic-scholar
Semantic Scholar1 events on 2026-05-01role: 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: mixture of experts inference serving Authors: Ananya Hegde, Akshata Kumble, Ravi Gupta Citations: 0 Mixture-of-Experts (MoE) architectures reduce inference cost by activating only a sparse subset of parameters per token. However, when these models exceed single-GPU memory,