> ## Content Index
> Fetch the complete content index at: https://orbiorbi.com/news/llms.txt
> Use this file to discover other available public pages before exploring further.

# llama.cpp b11720 prerelease adds non-contiguous SUM support
- URL: https://orbiorbi.com/news/en/hot/llama-cpp-b11720-noncontiguous-sum-en/
- Published: 2026-10-18T17:40:31.000Z
- Updated: 2026-10-18T23:00:41.000Z
- Description: According to ggml, the llama.cpp b11720 prerelease adds non-contiguous SUM support for CPU, CUDA, Vulkan and WebGPU backends, alongside test cases for SUM operations over non-contiguous views.
- Author: Orbis News
- Tags: #orbis-hot, #en

According to ggml, the llama.cpp b11720 prerelease adds non-contiguous SUM support for CPU, CUDA, Vulkan and WebGPU backends, alongside test cases for SUM operations over non-contiguous views.

## Sources and originals

- \[1\] ggml · 2026-10-19 · [Read original](https://github.com/ggml-org/llama.cpp/releases/tag/b11720?ref=orbiorbi.com)  
The prerelease notes add non-contiguous SUM support across several backends and related tests.

{"version":2,"hot":{"event\_id":"llama-cpp-b11720-noncontiguous-sum","group":"open-source","count":1,"heat":20,"verified":"confirmed","firstSeen":"2026-10-18T17:40:31.000Z","lastSeen":"2026-10-18T23:00:30.415Z","sources":\[{"n":"ggml","publisher":"ggml","u":"https://github.com/ggml-org/llama.cpp/releases/tag/b11720","say":"The prerelease notes add non-contiguous SUM support across several backends and related tests.","tier":"T0","at":"2026-10-18T17:40:31.000Z"}\],"signals":\[\],"facts":\[\]}}