# llama.cpp release b11799 adds SYCL q8 fast dequant support

> The open‑source llama.cpp library version b11799, published on Oct 21 2026, adds a SYCL fast‑dequant routine and provides new binaries for macOS, iOS and Linux.

Oossa · 2026-10-21 · https://oossa.com/en/llama-cpp-release-b11799-adds-sycl-q8-fast-dequant-support

The ggml‑org team released llama.cpp version b11799 on Oct 21 2026. The update adds a SYCL implementation for q8 fast dequantisation (pull #30775). It also ships pre‑built binaries for Apple Silicon, Intel Macs, iOS, and several Ubuntu configurations including Vulkan and CUDA 12.8.

## The facts

- Release tag: b11799
- Published: Wed Oct 21 2026

## Why it matters

Developers can now run llama.cpp with faster SYCL dequant on compatible GPUs, expanding hardware options for running LLMs locally.

## Sources & references

1. [ggml-org/llama.cpp b11799](https://github.com/ggml-org/llama.cpp/releases/tag/b11799) – llama.cpp, 2026-10-21

Last updated: 2026-10-21