GreedySnake: Accelerating SSD-Offloaded LLM Training with Efficient Scheduling and Optimizer Step Overlapping

Documenti analoghi

• EDGC: Entropy-driven Dynamic Gradient Compression for Efficient LLM Training
  di: Yi, Qingao, et al.
  Pubblicazione: (2025)
• Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage
  di: Yuan, Ziqi, et al.
  Pubblicazione: (2025)
• EcoSpa: Efficient Transformer Training with Coupled Sparsity
  di: Xiao, Jinqi, et al.
  Pubblicazione: (2025)
• ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
  di: Yin, Wangsong, et al.
  Pubblicazione: (2025)
• Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification
  di: Kermani, Arshia, et al.
  Pubblicazione: (2025)