HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving

Documenti analoghi

• Test-Time Speculation
  di: Kumar, Avinash, et al.
  Pubblicazione: (2026)
• HiSpec: Hierarchical Speculative Decoding for LLMs
  di: Kumar, Avinash, et al.
  Pubblicazione: (2025)
• CEEBERT: Cross-Domain Inference in Early Exit BERT
  di: Bajpai, Divya Jyoti, et al.
  Pubblicazione: (2024)
• TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference
  di: Jaber, Jaber, et al.
  Pubblicazione: (2026)
• Accelerating Large Language Model Inference with Self-Supervised Early Exits
  di: Valade, Florian
  Pubblicazione: (2024)