Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models

Documenti analoghi

• MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference
  di: Bambhaniya, Abhimanyu Rajeshkumar, et al.
  Pubblicazione: (2025)
• How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving
  di: Wu, Hanjiang, et al.
  Pubblicazione: (2026)
• TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Machine Learning
  di: Won, William, et al.
  Pubblicazione: (2023)
• HARP: A Taxonomy for Heterogeneous and Hierarchical Processors for Mixed-reuse Workloads
  di: Garg, Raveesh, et al.
  Pubblicazione: (2025)
• CELLO: Co-designing Schedule and Hybrid Implicit/Explicit Buffer for Complex Tensor Reuse
  di: Garg, Raveesh, et al.
  Pubblicazione: (2023)