view article Article Universal Assisted Generation: Faster Decoding with Any Assistant Model By danielkorat and 7 others • Oct 29, 2024 • 51
view article Article Faster Assisted Generation with Dynamic Speculation By jmamou and 6 others • Oct 8, 2024 • 46
view article Article Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding By ofirzaf and 10 others • Jan 30, 2024 • 9