4 papers
Memory Compression for High-Fanout Agent Sandboxes
Mengming Li, Ceyu XU, Qijun Zhang +4
High-fanout agent workloads create a growing memory bottleneck because a single task may spawn many concurrent sandbox sessions. Yet these sandboxes are far from independent: they…
ARGUS: Agentic GPU Optimization Guided by Data-Flow Invariants
Haohui Mai, Xiaoyan Guo, Xiangyun Ding +7
LLM-based coding agents can generate functionally correct GPU kernels, yet their performance remains far below hand-optimized libraries on critical computations such as matrix mult…
AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs
Ran Yan, Youhe Jiang, Tianyuan Wu +7
Maximizing training throughput and cost-efficiency of RL for LLMs is essential to democratize this advanced technique. One promising but challenging approach is to deploy such a co…
FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel
Ran Yan, Youhe Jiang, Zhuoming Chen +3
Recent advances in sparse attention mechanisms have demonstrated strong potential for reducing the computational cost of long-context training and inference in large language model…