Tag
This paper presents a two-stage methodology for end-to-end LLM deployment on spatial NPUs, progressing from human-guided development to an autonomous agent skill system. The system achieves speedups of 2.2x on prefill and 4.0x on decode for a reference model, and autonomously deploys eight additional LLMs on AMD XDNA 2 NPU with minimal human guidance.
This post describes how to use Hugging Face's ZeroGPU and a coding agent to autonomously deploy AI models, specifically the LongCat talking-avatar model, on a budget.