Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution

Documenti analoghi

• INSPIRIT: Optimizing Heterogeneous Task Scheduling through Adaptive Priority in Task-based Runtime Systems
  di: Wang, Yiqing, et al.
  Pubblicazione: (2024)
• LOw-cOst yet High-Performant Sparse Matrix-Matrix Multiplication on Arm SME Architectures
  di: Lei, Kelun, et al.
  Pubblicazione: (2025)
• FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning
  di: QI, Jiaxing, et al.
  Pubblicazione: (2024)
• Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers
  di: Lu, Yao, et al.
  Pubblicazione: (2026)
• PRAGMA: A Profiling-Reasoned Multi-Agent Framework for Automatic Kernel Optimization
  di: Lei, Kelun, et al.
  Pubblicazione: (2025)