# llama.cpp adds CUDA debug buffer pool in b12318 release

> The open‑source LLaMA inference library adds a CUDA debug buffer pool and updates binary builds for macOS, iOS and Linux.

Oossa · 2026-11-12 · https://oossa.com/en/llama-cpp-adds-cuda-debug-buffer-pool-in-b12318-release

ggml‑org released version b12318 of llama.cpp on 2026‑11‑12. The update adds a CUDA debug buffer pool to help developers track memory use with compute‑sanitizer. It also includes new pre‑built binaries for Apple Silicon, Intel macOS, iOS, and several Ubuntu CPU and Vulkan targets.

## The facts

- Release version b12318 published on 2026‑11‑12
- Adds CUDA debug buffer pool (#31919)

## Why it matters

Developers running LLaMA models on NVIDIA GPUs can now more easily debug memory issues, reducing crashes during inference.

## Sources & references

1. [ggml-org/llama.cpp b12318](https://github.com/ggml-org/llama.cpp/releases/tag/b12318) – llama.cpp, 2026-11-12

Last updated: 2026-11-12