Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling

Documenti analoghi

• Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation
  di: Das, Devleena, et al.
  Pubblicazione: (2025)
• Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management
  di: Zhang, Hang, et al.
  Pubblicazione: (2025)
• Automatic Generation of Fast and Accurate Performance Models for Deep Neural Network Accelerators
  di: Lübeck, Konstantin, et al.
  Pubblicazione: (2024)
• It's all about PR -- Smart Benchmarking AI Accelerators using Performance Representatives
  di: Jung, Alexander Louis-Ferdinand, et al.
  Pubblicazione: (2024)
• Silicon Showdown: Performance, Efficiency, and Ecosystem Barriers in Consumer-Grade LLM Inference
  di: Javat, Abdurrahman, et al.
  Pubblicazione: (2026)