LiteVLM: A Low-Latency Vision-Language Model Inference Pipeline for Resource-Constrained Environments

Documenti analoghi

• Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing
  di: Sung, Mingyu, et al.
  Pubblicazione: (2025)
• FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference
  di: Bajpai, Divya Jyoti, et al.
  Pubblicazione: (2025)
• Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments
  di: Kim, Hyunwoo, et al.
  Pubblicazione: (2025)
• Hybrid JIT-CUDA Graph Optimization for Low-Latency Large Language Model Inference
  di: Yadav, Divakar Kumar, et al.
  Pubblicazione: (2026)
• Outcome-Aware Tool Selection for Semantic Routers: Latency-Constrained Learning Without LLM Inference
  di: Chen, Huamin, et al.
  Pubblicazione: (2026)