Skip to content
AI NEWS JOURNAL
ONE EVENT. MANY PERSPECTIVES.

llama.cpp 发布 b11898 版本:修复 ARM 架构下 ggml-cpu 未使用变量问题,支持多平台与多加速后端

llama.cpp 于 2026-10-26 发布版本 b11898,主要修复 ggml-cpu 在 ARM 架构中未使用变量的问题(PR #31180);提供覆盖 macOS、iOS、Linux、Android、Windows 和 openEuler 的数十种二进制包,支持 CUDA 12.4/12.8/13.4、Vulkan、ROCm 10.0、OpenVINO 2026.4.1、SYCL(FP32/FP16)、Snapdragon(CPU/GPU/NPU)等后端;KleidiAI 版 macOS Apple Silicon 构建及部分 openEuler 构建被明确禁用。

1 independent sources · 1 reportsOldest first ↕
Newest first

b11898

ggml-cpu : fix unused variables in arm arch (#31180) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11898/llama-b11898-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11898/llama-b11898-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11898/llama-b11898-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11898/llama-b11898-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11898/llama-

Timeline and related coverage