Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training
Zili Wang, Zhaopeng Qiu, Yuekai Zhang +2
Speculative decoding accelerates rollout generation, which dominates the cost of reinforcement learning (RL) post-training. Online co-training can further increase the draft's accu…
cs.LG2026
AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving
Tianhao Xu, Yiming Liu, Xianglong Lu +18
Optimizing Large Language Model (LLM) inference in production systems is increasingly difficult due to dynamic workloads, stringent latency/throughput targets, and a rapidly expand…
cs.LG2026
FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning
Zhaopeng Qiu, Shuang Yu, Jingqi Zhang +4
Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence lengths make attention and KV-cache me…