Distributed Adaptive Speculative Decoding: Accelerating Large Language Model Inference With Context-Aware Draft Selection

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Distributed Adaptive Speculative Decoding: Accelerating Large Language Model Inference With Context-Aware Draft Selection
Συγγραφείς: Patel, Tejas Pravinbhai, Soni, Vinay R, Padhy, Amit Kumar, Bayyavarapu, Siva Rama Krishna Varma, Parikh, Milan
Πηγή: 2026 14th International Symposium on Digital Forensics and Security (ISDFS) Digital Forensics and Security (ISDFS), 2026 14th International Symposium on. :1-6 Mar, 2026
Relation: 2026 14th International Symposium on Digital Forensics and Security (ISDFS)
Βάση Δεδομένων: IEEE Xplore Digital Library