@article{koalaenhancingspeculativedecodingforllm, title = {KOALA: Enhancing Speculative Decoding for LLM via Multi-Layer Draft Heads with Adversarial Learning}, author = {Kaiqi Zhang and Jing Zhao and Rui Chen}, year = {2024}, eprint = {2408.08146}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.08146v1}, }