Xuan-1998/LPSim

GPU-accelerated, multi-GPU simulator for large-scale network flow and agent-based optimization: powers ICML 2026 deep-RL dispatch, MoE routing policies, and closed-loop LLM-driven fleet optimization over networks with hundreds of thousands of nodes and millions of agents.

语言：C++ · GitHub 星标：76 · Fork：3

话题：ai-for-science · cuda · deep-reinforcement-learning · gpu-computing · high-performance-computing · hpc · icml · large-scale-simulation

在 GitHub 上查看原仓库