Tag
Describes using ncnn's Vulkan backend for vendor-agnostic ML inference on production edge devices, achieving 10x speedup over CPU ONNX for face detection and embedding models.
Sharon Zhou proposes a vendor-agnostic, kernel-level GPU performance benchmark to help AI agents optimize compute efficiency for frontier models, and highlights AMD's AgentKernelArena as a starting point.
This paper presents Decoupled Search Grounding (DSG), a vendor-agnostic architecture that separates search retrieval from LLM reasoning, enabling explicit control over provider routing, caching, and output contracts. Experiments show DSG nearly matches native search accuracy at 91% lower cost and 68% lower latency.