Skip to content

Conversation

@rasbt
Copy link
Owner

@rasbt rasbt commented Nov 24, 2025

Removes the persistent=False setting from the KV cache tutorial because it would otherwise cause issues with loading the pre-trained weights as discussed here: https://magazine.sebastianraschka.com/p/coding-the-kv-cache-in-llms/comment/179549676

@rasbt rasbt merged commit a11965f into main Nov 25, 2025
3 checks passed
@rasbt rasbt deleted the rasbt-patch-1 branch November 25, 2025 02:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants