# llama.cpp v0.2.0 release fixes AMD iGPU slowdown

> The open‑source LLaMA inference library adds a Vulkan fix for AMD integrated graphics and updates pre‑built binaries for macOS, iOS and Linux.

Oossa · 2026-10-07 · https://oossa.com/en/llama-cpp-v0-2-0-release-fixes-amd-igpu-slowdown

The ggml‑org team released llama.cpp version b11461 on 2026-10-07. The update fixes a slow checkpoint read when using Vulkan on AMD integrated GPUs. It also provides new binary packages for Apple Silicon, Intel Macs, iOS, and several Linux builds (CPU, Vulkan, CUDA 12.8). Users can download the appropriate archive from the GitHub release page.

## The facts

- Release version b11461 published on 2026-10-07
- Vulkan fix addresses AMD iGPU performance issue

## Why it matters

AMD laptop users can now run LLaMA models faster without the previous slowdown.

## Sources & references

1. [ggml-org/llama.cpp b11461](https://github.com/ggml-org/llama.cpp/releases/tag/b11461) – llama.cpp, 2026-10-07

Last updated: 2026-10-07