activity
20232026
most citedThe Mamba in the Llama: Distilling and Accelerating Hybrid Models

2 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.LG2026

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System

Junxiong Wang, Fengxiang Bie, Jisen Li +14

Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone…