learn-kernels

Profile LLM with ATOM, extract GPU kernels, generate kernel inventory

Extract per-layer kernel sequence from ATOM level=3 traces

Launch ATOM server and run throughput benchmark

CUDA graph replay benchmark + source trace templates

Single GPU kernel micro-benchmark with roofline analysis

Deep kernel source-level walkthrough for aiter/atom/CK stack

Map complete kernel pipeline for LLM inference (prefill vs decode)