7 papers
ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training
Yukun Tian, Junwei Su, Haofeng Xu +6
Reinforcement learning (RL) has been a critical paradigm for improving large language model (LLM) reasoning and agentic capabilities, but its efficiency remains a major bottleneck.…
Reward-Aligned Reweighting for On-Policy Distillation
Haofeng Xu, Junwei Su, Lansong Diao +2
On-policy distillation (OPD) trains a student language model with dense feedback from a stronger teacher on student-generated trajectories. Yet standard OPD weights token-level dis…
GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control
Haofeng Xu, Junwei Su, Yukun Tian +3
Asynchronous execution is essential for scaling reinforcement learning (RL) to modern large model workloads, including large language models and AI agents, but it can fundamentally…
Are you going to finish that? A Practical Study of the Partial Token Problem
Hao Xu, Alisa Liu, Jonathan Hayase +2
Language models (LMs) are trained over sequences of tokens, whereas users interact with LMs via text. This mismatch gives rise to the partial token problem, which occurs when a use…
Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod
Ao Xiao, Bangzheng He, Baoquan Zhang +125
Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentr…
Infini-gram mini: Exact n-gram Search at the Internet Scale with FM-Index
Hao Xu, Jiacheng Liu, Yejin Choi +2
Language models are trained mainly on massive text data from the Internet, and it becomes increasingly important to understand this data source. Exact-match search engines enable s…
DeepServe: Serverless Large Language Model Serving at Scale
Junhao Hu, Jiang Xu, Zhixia Liu +18
In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addr…