SIGN IN SIGN UP

Fix memory bug in grammar parser (#7194)

The llama.cpp grammar parser had a bug where forgetting to add a closing
quotation mark to strings would cause parsing to crash. Anyone running a
server on a public endpoint is advised to upgrade. To reproduce this bug

    ./llamafile -m foo.gguf -p bar --grammar 'root::="'

Credit for discovering and reporting this issue goes to Eclypsium
Security Researcher Richard Johnson <Richard.johnson@eclypsium.com>.
J
Justine Tunney committed
4e3880978f8b1bf546dd4e6f3b524d6b8739c49c
Parent: f89fe27
Committed by GitHub <noreply@github.com> on 5/10/2024, 11:01:08 AM