Faster Speech-LLaMA Inference with Multi-token Prediction.

Desh Raj Gil Keren Junteng Jia Jay Mahadeokar Ozlem Kalinli Faster Speech-LLaMA Inference with Multi-token Prediction. 2024 abs/2409.08148 CoRR https://doi.org/10.48550/arXiv.2409.08148 db/journals/corr/corr2409.html#abs-2409-08148 streams/journals/corr