# llama.cpp b11977 fixes OpenVINO SCALE view handling

> The release fixes a bug that could scale an entire source tensor instead of a sliced view, potentially overrunning the result buffer.

Oossa · 2026-10-29 · https://oossa.com/en/llama-cpp-b11977-fixes-openvino-scale-view-handling

ggml-org’s llama.cpp release b11977 fixes how its OpenVINO backend handles SCALE operations on sliced tensor views. Previously, a strided view could be treated as its full source tensor, producing an oversized result and potentially crashing tests.

The fix processes the view as a slice and rejects in-place SCALE on non-contiguous views, where copying the result back could write to the wrong elements. The release also lists builds for platforms including macOS, Linux, Android and Windows.

## The facts

- The change is tracked as pull request #31334.
- The release lists OpenVINO builds for Ubuntu x64 and Windows x64.

## Why it matters

For developers using llama.cpp’s OpenVINO backend with sliced tensor inputs, this fixes a case that could crash tests or write results to the wrong elements.

## Sources & references

1. [ggml-org/llama.cpp b11977](https://github.com/ggml-org/llama.cpp/releases/tag/b11977) – llama.cpp, 2026-10-29

Last updated: 2026-10-29