Tag: edge AI
Browse our exclusive articles!
DUAL-BLADE: Optimized NVMe KV-Cache for Edge LLM Inference
Discover DUAL-BLADE's dual-path NVMe KV-cache offloading that boosts edge LLM inference by reducing latency and improving memory efficiency.
Low-Precision NAS for Spaceborne Edge AI Deployment
Optimize neural networks with deployment-aligned low-precision NAS for efficient, accurate spaceborne edge AI on resource-constrained devices.
LARS: Memory-Efficient Fine-Tuning for On-Device LLMs
Discover how LARS reduces memory use in fine-tuning large language models on devices with limited resources, boosting efficiency without performance loss.
PLaMo 2.1-VL: Advanced Vision Language Model for Industry
Discover PLaMo 2.1-VL, a lightweight Vision Language Model optimized for Japanese-language operation in industrial AI applications.
Edge Deployment & Acceleration of Multi-LoRA LLM on Devices
Discover efficient edge deployment and on-device acceleration of multi-LoRA enabled foundational LLMs for faster, smarter AI on smartphones.