Hybrid-Parallel: Achieving High Performance and Energy Efficient Distributed Inference on Robots

Documenti analoghi

• Hecate: Unlocking Efficient Sparse Model Training via Fully Sharded Sparse Data Parallelism
  di: Qing, Yuhao, et al.
  Pubblicazione: (2025)
• HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference
  di: Lin, Haoran, et al.
  Pubblicazione: (2025)
• Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs
  di: Chen, Aodong, et al.
  Pubblicazione: (2023)
• Amoeba: Runtime Tensor Parallel Transformation for LLM Inference Services
  di: Chen, Haoyu, et al.
  Pubblicazione: (2025)
• CoCoDiff: Optimizing Collective Communications for Distributed Diffusion Transformer Inference Under Ulysses Sequence Parallelism
  di: Ma, Bin, et al.
  Pubblicazione: (2026)