MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference

Documenti analoghi

• Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models
  di: Bambhaniya, Abhimanyu, et al.
  Pubblicazione: (2024)
• 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)
• Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
  di: Bambhaniya, Abhimanyu Rajeshkumar, et al.
  Pubblicazione: (2024)
• TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Machine Learning
  di: Won, William, et al.
  Pubblicazione: (2023)
• H3DFact: Heterogeneous 3D Integrated CIM for Factorization with Holographic Perceptual Representations
  di: Wan, Zishen, et al.
  Pubblicazione: (2024)