2 papers
cs.DC2026
Tangram: Hiding GPU Heterogeneity for Efficient LLM Parallelization
Yanda Tao, Pedro F. Silvestre, Marcel Wagenländer +1
The scale of LLM training jobs requires parallelization planning over large GPU clusters. Due to different GPU types and interconnects added over time, these GPU clusters are incre…
cs.DC2026
Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
Marcel Wagenländer, Otto White, Britannio Jarrett +6
Agentic workflows carry out complex tasks by orchestrating multiple large language models (LLMs) and tools. Serving such workflows at a target throughput with low latency is challe…