Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Bibliografske podrobnosti

izdano v:	arXiv.org (Dec 8, 2024), p. n/a
Glavni avtor:	Akhiad Bercovich
Drugi avtorji:	Ronen, Tomer, Abramovich, Talor, Ailon, Nir, Nave Assaf, Dabbah, Mohammad, Galil, Ido, Geifman, Amnon, Geifman, Yonatan, Golan, Izhak, Haber, Netanel, Karpas, Ehud, Koren, Roi, Levy, Itay, Molchanov, Pavlo, Mor, Shahar, Zach, Moshe, Nabwani, Najeeb, Puny, Omri, Rubin, Ran, Schen, Itamar, Shahaf, Ido, Tropp, Oren, Omer Ullman Argov, Zilberstein, Ran, El-Yaniv, Ran
Izdano:	Cornell University Library, arXiv.org
Teme:	Computing costs Integer programming Mixed integer Computer architecture Large language models Graphics processing units Hardware Constraints Parameters Inference
Online dostop:	Citation/Abstract Full text outside of ProQuest
Oznake:	Označite Brez oznak, prvi označite!