ggerganov/llama.cpp b7958: b7958
AI Summary
The article discusses the release of version b7958 of the ggerganov/llama.cpp project, which is a C++ port of the Llama language model. The key points include: 1. The release includes a fix for a MSVC regex error related to Unicode handling (#19340). 2. The code comments have been updated to use `const_iterator` and remove specializations. 3. The release provides pre-built binaries for various platforms, including macOS (Apple Silicon and Intel), iOS, Linux (Ubuntu x64 CPU and Vulkan, Ubuntu s390x CPU), Windows (x64 CPU, arm64 CPU, CUDA 12, CUDA 13, Vulkan, SYCL, HIP), and openEuler (x86 and aarch64). Overall, this release focuses on improving the stability and compatibility of the ggerganov/llama.cpp project, making it more accessible to users across different operating systems and hardware configurations.
Original Description
<details open> unicode : MSVC regex fix (#19340) * Fix model loading regex error * Change comments * Use const_iterator and remove specializations --------- Co-authored-by: Alde Rojas <hello@alde.dev> </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b7958/llama-b7958-bin-macos-arm64.tar.gz) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b7958/llama-b7958-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b7958/llama-b7958-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b7958/llama-b7958-bin-ubuntu-x64.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b7958/llama-b7958-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b7958/llama-b7958-bin-ubuntu-s390x.tar.gz) **Windows:** - [Windows x
Details
Discussion coming soon...