# llama.cpp v b12362 adds grammar parsing improvements

> The open‑source llama.cpp library released version b12362 on Nov 13 2026, adding left‑factorization and an AST for grammar handling.

Oossa · 2026-11-13 · https://oossa.com/en/llama-cpp-v-b12362-adds-grammar-parsing-improvements

ggml‑org released llama.cpp version b12362. The update introduces left‑factorization to speed up grammar matching, adds an abstract syntax tree for parsing, and limits alternative rules. Some recent commits were reverted to keep the parser stable. The build now supports a wide range of platforms, from macOS Apple Silicon to Windows CUDA 13.

The release notes list support for Linux, Android, Windows, and various GPU back‑ends such as Vulkan and OpenCL.

## The facts

- Version b12362 released on 2026-11-13.
- Adds left‑factorization optimization and an AST for grammar parsing.

## Why it matters

Developers can run LLMs with faster, more reliable grammar handling across many devices.

## Sources & references

1. [ggml-org/llama.cpp b12362](https://github.com/ggml-org/llama.cpp/releases/tag/b12362) – llama.cpp, 2026-11-13

Last updated: 2026-11-13