diff options
| author | Justine Tunney <jtunney@mozilla.com> | 2024-05-10 07:01:08 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-10 21:01:08 +1000 |
| commit | 4e3880978f8b1bf546dd4e6f3b524d6b8739c49c (patch) | |
| tree | 54ab13653c57d8a5ecb709947dd5a43596ca64c2 /examples/json_schema_to_grammar.py | |
| parent | f89fe2732c5709f6e86d5f4aee2e6d2a561f2eb2 (diff) | |
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>.
Diffstat (limited to 'examples/json_schema_to_grammar.py')
0 files changed, 0 insertions, 0 deletions