The latest b9663 release of llama.cpp focuses on enhancing SYCL support, adding operations such as EXPM1 and ensuring all unit test cases for FLOOR, TRUNC, and ROUND are covered. The update also resolves conflicts and supports new unit test cases for repeat and concat operations. Platform support is expanded across macOS, Linux, Windows, and openEuler, improving compatibility and performance. This release strengthens llama.cpp's utility for developers, though it doesn't introduce any major new features.
Read originalThe latest b9653 release of llama.cpp continues its trend of broadening platform compatibility, notably adding Vulkan support for Ubuntu and Windows, and ROCm 7.2 for Ubuntu x64. While KleidiAI support for macOS Apple Silicon is disabled, the release still offers a wide array of builds across macOS, Linux, Windows, and openEuler. This update doesn't introduce new models or quantization methods but focuses on making llama.cpp more accessible across diverse hardware configurations. Developers can now leverage these enhancements to optimize AI inference on a wider range of systems.
The latest b9654 release of llama.cpp continues its trend of broadening platform compatibility, though without major new features. Notably, the release includes support for ROCm 7.2 on Ubuntu x64, which is significant for AMD GPU users seeking alternatives to NVIDIA's CUDA. While KleidiAI support on macOS Apple Silicon is disabled, the release still covers a wide array of systems, including Windows with CUDA 12 and 13 DLLs. This update reinforces llama.cpp's commitment to being a versatile inference runtime across diverse hardware configurations.
OpenEnv is evolving into a pivotal open-source tool for agentic reinforcement learning (RL), now backed by a coalition of major AI organizations including Meta-PyTorch, Nvidia, and Hugging Face. This initiative aims to standardize the interface between RL environments and trainers, promoting interoperability and efficiency. By serving as a common socket for various RL components, OpenEnv facilitates seamless integration across different ecosystems. This move is set to enhance the development of specialized models and harnesses, making RL more accessible and efficient for the open-source community.
© Lev SelectorJetBrains has open-sourced Mellum2, a 12 billion parameter mixture of experts model.