AI Infra Interviews logo

Guided lab: prove what the cache changed

Check the input trace and generated token IDs before comparing cached and uncached timings. Report all six paired results and their spread, and explain the memory cost of keeping attention state between steps.

30 MIN · PREMIUM

This lesson is part of Premium, which includes all concepts, course lessons and answers.

Get Premium · ₹2,000 / $256 months of access · one payment · no auto-renew