yunwei37·Oct 17When Does CPU Scheduling Help AI Inference?LLM inference is usually discussed as a GPU problem. That framing is mostly right: matrix multiplication, attention, KV-cache access, and…
yunwei37·Jul 15An Empirical Study: AI Agent Rules Need Context and Layered EnforcementA rule like “run the full test suite before committing” looks simple until an AI coding agent edits a source file after the last test run…