ConFu: Contemplate the Future for Better Speculative Sampling
arXiv:2603.08899v1 Announce Type: new Abstract: Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models …
Zongyue Qin, Raghavv Goel, Mukul Gagrani, Risheek Garrepalli, Mingu Lee, Yizhou Sun
조회수 26회