conftrace_

large model training

4 papers

Explore in graph

Also known as

LMT

Co-occurring keywords · papers mentioning both

distributed training (2) meta model (1) module incubation (1) performance troubleshooting (1) online profiling (1) differential observability (1) kernel scheduling (1) frequency scaling (1) time-energy tradeoff (1) sub-module training (1)

Papers

Attack of the Bubbles: Straggler-Resilient Pipeline Parallelism for Large Model Training NSDI 2026 EROICA: Online Performance Troubleshooting for Large-scale Model Training NSDI 2026 Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training OSDI 2026 Deep Incubation: Training Large Models by Divide-and-Conquering ICCV 2023