abetlen / abetlen/llama-cpp-python

llama_get_kv_self debug symbols removed

Open
#2,064 0 comments 1 reaction 0 assignees View on GitHub
Dominant language
Python
Stars
10.6k
Forks
1.4k
PR merge metrics
PR metrics pending

Description

# Prerequisites

Please answer the following questions for yourself before submitting an issue.

- [x] I am running the latest code. Development is very rapid so there are no tagged versions as of now.
- [x] I carefully followed the [README.md](https://github.com/abetlen/llama-cpp-python/blob/main/README.md).
- [x] I [searched using keywords relevant to my issue](https://docs.github.com/en/issues/tracking-your-work-with-issues/filtering-and-searching-issues-and-pull-requests) to make sure that I am creating a new issue that is not already open (or closed).
- [x] I reviewed the [Discussions](https://github.com/abetlen/llama-cpp-python/discussions), and have a new bug or useful enhancement to share.

# Expected Behavior

Debugpy should not have issues debugging the application itself.

# Current Behavior

In actual development run *without* debugger, no issues with the latest binary.

This behaviour only occurs when DebugPy is being used to step through the processes.

# Environment and Context

* MacOS Sequoia
* Python 3.13
* Llama-cpp @ b6370
* Llama-cpp-python @ 3.16

# Failure Information

Image

An attribute error occurs as the debug symbol was removed 2 weeks back (mid aug 2025), see [libllama api changelog](https://github.com/ggml-org/llama.cpp/issues/9289).

# Reproduce

This is my .vscode/launch.json settings for DebugPy

```json
{
"version": "0.2.0",
"configurations": [
{
"_comment": "This only runs on current file instance.",
"type": "python",
"request": "launch",
"name": "Standalone File Debugger",
"program": "${file}",
"console": "integratedTerminal",
"justMyCode": false,
},
]
}

```

On MacOS, the libllama.dylib might need to be updated to reflect changes of the API.

Thanks for the developing this project, not a major issue unless the debugger is needed to step through the process.

Note: installing Llama.cpp binary @ commit: b6188 allows debugging as symbols still exists (did not test other commits).

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.