cs.AR · 2026-11-14 · No. 171
Hardware Architecture, 2026-11-14.
2 new papers in cs.AR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
2 entries-
01
Broadcast, Don't Replicate: Eliminating Weight HBM in Datacenter LLM Serving
Hannah Atmer, Yuan Yao, Thiemo Voigt, Stefanos Kaxiras
cs.AR · cs.DC · cs.ET · cs.NI
Large language model (LLM) inference at datacenter scale is fundamentally bottlenecked by memory capacity and bandwidth limits. Because model weights are read-only and identical across instances, conventional architectures that replicate these parameters across the local DRAM of tens of thousands of accelerators incur massive capital expenditures, significant static power dissipation, and redundant memory-fetch energy. A recent proposal to...
-
02
Infrastructure for Verifiable AI: Where Proof Costs Go and How Hardware Can Help
Yihan Xia, Wenxin Xu, Taotao Wang
cs.AR · cs.CR · cs.LG
Users of artificial intelligence services, including those powered by large language models and other transformer-based models, need assurance that inference and training follow the declared computation without exposing private models or data. Zero-knowledge proofs can provide this assurance, but proof generation remains expensive. Hardware acceleration research often reports gains for individual cryptographic operations, leaving their effect...
This edition is part of The Daily Abstract — cs.AR archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.