Tag: profiling

A Python performance playbook for choosing data structures, profiling tools, vectorized libraries, JIT experiments, and concurrency changes from evidence instead of taste.

Outcome: Provided a performance triage workflow that asks for a measured bottleneck before changing algorithms, data structures, runtime flags, concurrency models, or native libraries.

A repeatable triage routine — the three-run baseline, DataLoader diagnosis, five profiler signatures, and a copy-paste scaffold — for finding where training time actually goes before touching the model.

Outcome: Identified and resolved training bottlenecks in under an hour by running the three-run baseline and reading profiler signatures before changing any model code.