Loading your workspace…
Loading your workspace…
Due today
Distinguish raw KV capacity, allocator fragmentation, decode bandwidth, and scheduling head-of-line blocking. Name the measurements and one targeted intervention for each failure mode.
Demonstrated, not opened
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.
Recall before reference
Distinguish raw KV capacity, allocator fragmentation, decode bandwidth, and scheduling head-of-line blocking. Name the measurements and one targeted intervention for each failure mode.
Enter to send · Shift+Enter for a new line