SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs

Documenti analoghi

• CoCoDiff: Optimizing Collective Communications for Distributed Diffusion Transformer Inference Under Ulysses Sequence Parallelism
  di: Ma, Bin, et al.
  Pubblicazione: (2026)
• Minuet: Accelerating 3D Sparse Convolutions on GPUs
  di: Yang, Jiacheng, et al.
  Pubblicazione: (2023)
• Tally: Non-Intrusive Performance Isolation for Concurrent Deep Learning Workloads
  di: Zhao, Wei, et al.
  Pubblicazione: (2024)
• Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents
  di: Song, Kevin, et al.
  Pubblicazione: (2025)
• Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization
  di: Zhu, Zhanda, et al.
  Pubblicazione: (2025)