Implement temperature + top- $k$ + top- $p$ sampling from a logits vector in numpy

Easy

Prefill, Decode, and KV Cache Memory1 / 5

Chapter 021 / 5

Prefill, Decode, and KV Cache Memory

Implement temperature + top- $k$ + top- $p$ sampling from a logits vector in numpy

Easy

Target interface

sample(logits, temperature=1.0, top_k=0, top_p=1.0, rng=None)

Complete the starter code in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.

solution.pyPython

Local draft

import numpy as np

def sample(logits, temperature=1.0, top_k=0, top_p=1.0, rng=None):
    raise NotImplementedError

def _softmax(x):
    raise NotImplementedError

Local draft

⌘/Ctrl↵to submit

AI review

Ready when you are

Submit your solution for a score and feedback on correctness, edge cases, and clarity. Any correct approach is accepted.

Chapter 021 / 5

Prefill, Decode, and KV Cache Memory

Implement temperature + top- $k$ + top- $p$ sampling from a logits vector in numpy

Easy

Target interface

sample(logits, temperature=1.0, top_k=0, top_p=1.0, rng=None)

Complete the starter code in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.