Loading your workspace…
Loading your workspace…
One concept at a time
For engineers building foundations, closing a gap, or preparing for an interview. Basic programming is enough to begin; ask for any unfamiliar math along the way.
Pick a topic to practise explaining mechanisms and defending tradeoffs. The tutor starts with an example before asking you to try.
Due today
Derive how online softmax keeps tiled attention exact. State the running row state, show how a later larger maximum rescales prior contributions, and separate the arithmetic complexity from the HBM-traffic improvement.
Recall summary
Concept path
Attention and position must both produce evidence before KV-cache probes enter the queue.
Weakness map
Need a first explanation instead?
Browse the topic library or work through a concept step by step.
Enter to send · Shift+Enter for a new line