
Title |
|---|
![]() ReLU Strikes Back: Exploiting Activation Sparsity in Large Language
ModelsInternational Conference on Learning Representations (ICLR), 2023 |
![]() Speculative Decoding: Exploiting Speculative Execution for Accelerating
Seq2seq GenerationConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |