llama.cpp 发布: b11120

来源摘要

vulkan: hide internal symbols to prevent duplicate-dlopen state destruction (#29139) Since #28732 our internal symbols are exported. A duplicate copy dlopened and dlclosed by ggml_backend_load_all() then interposes them, so its destructors destroy the live vk_instance and later device queries hit the GGML_ASSERT on vk_instance.device_indices. Hidden visibility exports only GGML_BACKEND_API, as before #28732. Fixes #29138 Assisted-by: henk:claude-fable-5 **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11120/llama-b11120-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/b11120/llama-b11120-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11120/llama-b11120-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11120/llama-b11120-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11120/llama-b11120-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11120/llama-b11120-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11120/llama-b11120-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11120/llama-b11120-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11120/llama-b11120-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.co