# llama.cpp release b11706 fixes SYCL prompt regression

> Version b11706 adds a SYCL fix for prompt‑processing and provides new binary builds for macOS, iOS, Linux, Vulkan and CUDA.

Oossa · 2026-10-17 · https://oossa.com/en/llama-cpp-release-b11706-fixes-sycl-prompt-regression

The open‑source llama.cpp library released version b11706 on 2026-10-17. The update fixes a regression in SYCL prompt processing that appeared after weight reordering for Q4_0/Q8_0 formats. It also ships new pre‑built binaries for macOS Apple Silicon, Intel, iOS, and various Linux configurations including CPU, Vulkan and CUDA 12.8. The builds are available for download from the GitHub release page.

## The facts

- Version b11706 released on 2026-10-17
- Fix addresses SYCL prompt‑processing regression after Q4_0/Q8_0 weight reorder

## Why it matters

Developers can now run llama.cpp on SYCL‑compatible GPUs without prompt‑handling errors, expanding hardware options for local LLM use.

## Sources & references

1. [ggml-org/llama.cpp b11706](https://github.com/ggml-org/llama.cpp/releases/tag/b11706) – llama.cpp, 2026-10-17

Last updated: 2026-10-17