3 papers
cs.DC2026
Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving
Zhixin Wang, Zhengbo Wang, Fangcheng Fu +15
Heterogeneous prefill-decode (PD) inference is now in production: prefill on cost-efficient or supply-available accelerators, decode on bandwidth-strong ones, and KV state crossing…
cs.DC2026
PlexRL: Cluster-Level Orchestration of Serviceized LLM Execution for RLVR
Yiqi Zhang, Fangzheng Jiao, Tian Tang +13
Reinforcement learning with verifiable rewards (RLVR) has recently unlocked strong reasoning capabilities in large language models (LLMs), triggering rapid exploration of new algor…
cs.PF2025
Memory Analysis on the Training Course of DeepSeek Models
Ping Zhang, Lei Su
We present a theoretical analysis of GPU memory consumption during the training of DeepSeek models such as DeepSeek-v2 and DeepSeek-v3. Our primary objective is to clarify the devi…