Junhan Shi
- D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding
2026/07/16 by Tianyu Liu, Yuhao Shen, Rui Cen +7
#cs.CL
- AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding
2026/07/28 by Hong Liu, Rui Cen, Junhan Shi +10
Computer Science · #cs.CL