How should I practice Grouped-Query Attention with a KV Cache?

Start by reading the full statement, solve the visible examples, then compare the pattern against related Amazon onsite interview problems in FastPrep.

Is Grouped-Query Attention with a KV Cache associated with Amazon?

FastPrep tags this as a Amazon onsite interview coding practice problem when the problem catalog has that company and stage context.

Grouped-Query Attention with a KV Cache

Amazon● HardFULLTIMEONSITE INTERVIEW

Problem statement

Compute one projection-free grouped-query scaled dot-product attention pass using an existing key-value cache plus newly generated key and value rows.

query has width queryHeads * headDim. Every cached or new key and value row has width kvHeads * headDim. Append the new rows after the cached rows for the attention calculation. queryHeads is divisible by kvHeads; each consecutive group of queryHeads / kvHeads query heads shares one key-value head.

The problem statement continues

Pro

Examples

Example 1

query = [[1]]cachedKey = []cachedValue = []newKey = [[0],[1]]newValue = [[10],[20]]queryHeads = 1kvHeads = 1return = ["17.310586"]

With one head and no cache, this is ordinary scaled dot-product attention.

FastPrep Pro

Reported in 1 Amazon interview this week

Unlock this recently reported problem

FastPrep Pro gives you full access to interview problems reported within the last week.

Full problem statement and constraints
2 more worked examples, explained
Guided hints and editorial
Run your code on real test cases

$8.25/month

$99 billed yearly — or $19 month-to-month. Cancel anytime.

Free plan — 2 of 2 free unlocks used this week

See Amazon hiring insights