Open Source
llama.cpp b9567 release expands platform support
llama.cpp Releaseshigh confidence
Why it matters
- →Expands platform support, making llama.cpp more versatile.
- →Enhances GPU performance on Windows with CUDA updates.
- →Highlights ongoing development challenges with some disabled features.
The latest b9567 release of llama.cpp focuses on expanding platform support, particularly for Linux and Windows users. Notably, Ubuntu now includes ROCm 7.2 and Vulkan support, while Windows benefits from CUDA 12 and 13 DLLs, enhancing GPU capabilities. However, some features like KleidiAI on macOS and SYCL on Windows remain disabled, suggesting areas still under development. This update reflects llama.cpp's ongoing efforts to cater to a wide range of hardware environments.
Read originalMore from llama.cpp Releases
Models & Labsmodels
llama.cpp b9561 Release Expands Platform Support
The b9561 release of llama.cpp continues to enhance its platform reach, adding Vulkan support for Ubuntu and Windows, and ROCm 7.2 for Ubuntu, which is a significant boost for AMD GPU users. While features like KleidiAI on macOS and SYCL on Windows remain inactive, this update reinforces llama.cpp's role as a flexible inference runtime across various systems. Although no new models are introduced, the release focuses on strengthening the existing infrastructure, making it more adaptable for developers working with different hardware setups. This ongoing expansion of capabilities ensures that llama.cpp remains a vital tool for AI inference across a broad spectrum of environments.
llama.cpp Releases
Models & Labsmodels
llama.cpp b9562 adds video input support
The latest b9562 release of llama.cpp introduces video input support, marking a significant step in expanding its capabilities. This update includes a new mtmd_helper_video feature and allows video input on servers via base64 encoding. The CLI has been updated to support video arguments, enhancing user interaction. While the release doesn't introduce new models, it broadens the scope of llama.cpp by integrating video processing, making it more versatile for developers working with multimedia inputs.
llama.cpp Releases
Open Sourcemodels
Llama.cpp b9564 Release Enhances WebGPU Support
The b9564 release of llama.cpp marks a notable enhancement in WebGPU capabilities, specifically through the implementation of 2D workgroups for operations like scale, binary, and unary functions. This update is designed to boost performance across macOS, Linux, and Windows systems. While the KleidiAI feature on Apple Silicon remains inactive, the release broadens hardware compatibility, including Vulkan and ROCm 7.2 support on Ubuntu. By refining these technical aspects, llama.cpp becomes a more flexible tool for developers dealing with a range of computing environments, making it a valuable asset for those working with CUDA and other advanced configurations.
llama.cpp Releases
More in Open Source
© Hugging Face BlogOpen Sourceagents
OpenEnv Gains Open Source Community Support
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.
Hugging Face Blog
© Lev SelectorOpen Sourcemodels
JetBrains Releases Mellum2 12B MoE Open-source
JetBrains has open-sourced Mellum2, a 12 billion parameter mixture of experts model.
Lev Selector
© Google Research BlogOpen Sourceresearch
Google Open Sources AI Hydrology Model for Flood Forecasting
Google has open-sourced its advanced AI-based hydrology model, aiming to enhance global flood forecasting capabilities. This move allows National Meteorological and Hydrological Services to integrate sophisticated AI tools into their workflows, potentially improving the accuracy and timeliness of flood warnings. By releasing the model on GitHub, Google empowers local experts to refine and adapt the technology using their own data, fostering a more resilient approach to flood management. This initiative democratizes access to cutting-edge forecasting tools, especially benefiting regions with limited resources.
Google Research Blog