# llama.cpp release fixes tool‑call memory bug

> The Oct 4 2026 update to llama.cpp clears a dangling pointer that could cause crashes during tool calls.

Oossa · 2026-10-04 · https://oossa.com/en/llama-cpp-release-fixes-tool-call-memory-bug

The open‑source LLM runtime llama.cpp released version b11393 on Oct 4 2026. The change fixes a use‑after‑free bug that occurred when a TOOL_ID node arrived after a TOOL_CLOSE event. The code now clears the current_tool pointer when the pending_tool_call is reset, preventing a second free of the same buffer.

## The facts

- Release date: Oct 04 2026
- Fix clears current_tool pointer on pending_tool_call reset

## Why it matters

Developers using llama.cpp will see fewer crashes when their applications make sequential tool calls.

## Sources & references

1. [ggml-org/llama.cpp b11393](https://github.com/ggml-org/llama.cpp/releases/tag/b11393) – llama.cpp, 2026-10-04

Last updated: 2026-10-04