Practice
Learn
← Quit
0 / 0 correct
LLMs & AI
Hard
1 of 20
Why do grouped-query attention (GQA) and multi-query attention (MQA) speed up inference?
A
They remove attention entirely
B
Several query heads share the same key/value heads, shrinking the KV cache and memory traffic
C
They increase the number of KV heads
D
They only affect training