AI & ML interests
Decentralized AI computing, distributed inference, edge AI, on-device AI, heterogeneous computing, NPU acceleration, efficient LLM inference, deterministic-first AI execution, agentic AI, AI agent orchestration, intelligent model routing, inference cost optimization, structured memory, GraphRAG, small language models (SLMs), and open-source AI infrastructure. We focus on reducing unnecessary model invocations, improving AI workload efficiency, and making AI computing more accessible through distributed devices.
Recent Activity
Krako-Labs 's datasets
None public yet