Towards Fully-fledged GPU Multitasking via Proactive Memory Scheduling
cs.OS
Submitted: 2025-12-31
Updated: 2026-11-06
Code: https://github.com/ggmlorg/llama.cpp
Terminology
Sources
- Generative AI in Multimodal User Interfaces: Trends, Challenges, and Cross-Platform Adaptability
- Microsecond-scale Dynamic Validation of Idempotency for GPU Kernels
- LoHan: Low-Cost High-Performance Framework to Fine-Tune 100B Model on a Consumer GPU
- Towards Real Smart Apps: Investigating Human-AI Interactions in Smartphone On-Device AI Apps
- PowerInfer-2: Fast Large Language Model Inference on a Smartphone