4 papers
ExaServe: Large-Scale LLM Serving on Exascale HPC Systems
Wenyi Wang, Shu Shi, Yadu Babuji +2
Cloud-native LLM serving frameworks have made deployment routine in data centers, yet deploying them on leadership-class supercomputers remains an engineering challenge requiring s…
HyGra: Accelerating Network-State Simulation for LLM Training in DCNs via Adaptive Packet-Flow Granularity
Wenyi Wang, Zheng Wu, Yanmeng Wang +4
In recent years, large language models (LLMs) have driven substantial intelligent transformation across diverse industries. Commercial LLM training is typically performed over data…
Optimizing Fine-Grained Parallelism Through Dynamic Load Balancing on Multi-Socket Many-Core Systems
Wenyi Wang, Maxime Gonthier, Poornima Nookala +4
Achieving efficient task parallelism on many-core architectures is an important challenge. The widely used GNU OpenMP implementation of the popular OpenMP parallel programming mode…
UpDown: Programmable fine-grained Events for Scalable Performance on Irregular Applications
Andronicus Rajasukumar, Jiya Su, Yuqing +12
Applications with irregular data structures, data-dependent control flows and fine-grained data transfers (e.g., real-world graph computations) perform poorly on cache-based system…