Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques

Documenti analoghi

• Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
  di: He, Shwai, et al.
  Pubblicazione: (2025)
• Efficiently Editing Mixture-of-Experts Models with Compressed Experts
  di: He, Yifei, et al.
  Pubblicazione: (2025)
• What Matters in Transformers? Not All Attention is Needed
  di: He, Shwai, et al.
  Pubblicazione: (2024)
• MoEless: Efficient MoE LLM Serving via Serverless Computing
  di: Yu, Hanfei, et al.
  Pubblicazione: (2026)
• PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model
  di: Liu, Yilun, et al.
  Pubblicazione: (2024)