Open Source
llama.cpp b9351 Release Expands Platform Support
llama.cpp Releaseshigh confidence
Why it matters
- →Expands support for AMD GPUs with ROCm 7.2, improving performance.
- →Enhances ARM-tuned capabilities on macOS with KleidiAI support.
- →Strengthens llama.cpp's role as a versatile inference runtime across platforms.
The latest b9351 release of llama.cpp introduces expanded support for various platforms, including ROCm 7.2 on Ubuntu x64, which benefits AMD GPU users. It also enables KleidiAI on macOS Apple Silicon, enhancing ARM-tuned performance for M-series Macs. While some features like SYCL FP32 remain disabled, the release focuses on improving platform compatibility rather than introducing new models. This update reinforces llama.cpp's position as a versatile tool for AI inference across multiple operating systems.
Read originalMore from llama.cpp Releases
Models & Labsmodels
Llama.cpp b9329 Release Enhances CUDA Performance
The b9329 release of llama.cpp brings a notable performance enhancement with the integration of a fast Walsh-Hadamard transform for CUDA, which is set to improve computational efficiency. This update also includes optimizations such as unrolling and changes from size_t to int, aimed at boosting processing speed. The release is compatible with platforms like macOS, Linux, Windows, and openEuler, ensuring developers can leverage these improvements across different environments. While there are no new models introduced, the emphasis on performance optimization makes this update significant for those working with CUDA and other supported systems.
llama.cpp Releases
Models & Labsmodels
llama.cpp b9330 release improves model performance
The b9330 release of llama.cpp resolves a key issue by correctly tagging the ffn_latent operation as MUL_MAT, aligning it with the backend's operational expectations. This correction ensures that weights and their matrix multiplications remain on the GPU, avoiding unnecessary CPU fallback and graph splitting. As a result, performance on the Nemotron 3 Super 120B Q5_K_M model has significantly improved, with throughput increasing from 64.9 to 103.22 tokens per second. This update reflects llama.cpp's dedication to enhancing AI model performance across different computing environments, including macOS with KleidiAI and Ubuntu with ROCm 7.2. By maintaining efficient GPU processing, llama.cpp continues to optimize AI model execution, ensuring robust performance on platforms like CUDA 12 and CUDA 13.
llama.cpp Releases
Open Sourcemodels
llama.cpp b9331 Release Enhances CI Workflows
The b9331 release of llama.cpp brings a strategic overhaul to its continuous integration workflows, focusing on efficiency by isolating tasks into separate workflows. This update includes the extraction of Android and HIP tasks, alongside the relocation of WebGPU and RPC tasks into distinct workflows. Additionally, the release halts SYCL f16 builds and optimizes pull request jobs by aligning backend paths. While there are no new model architectures introduced, this release aims to streamline development processes and enhance build management across diverse environments.
llama.cpp Releases
More in Open Source
© Lev SelectorOpen Sourcemodels
Karpathy Open-Sources CLAUDE md
Andrej Karpathy has released CLAUDE md as open source.
Lev Selector
© Matt WolfeOpen Sourcemusic
Stable Audio 3.0 Released for Artistic Experimentation
Stability AI has launched Stable Audio 3.0, a model family designed for artistic experimentation with open-weight models.
Matt Wolfe
© GitHub ChangelogOpen Sourcecoding
GitHub Copilot for Eclipse Goes Open Source
GitHub has open-sourced its Copilot plugin for Eclipse, marking a significant step in integrating AI-powered tools within the Eclipse ecosystem. By releasing the code under the MIT license, GitHub invites developers to explore, contribute, and innovate on how AI enhances developer experiences in Eclipse. This move not only promotes transparency but also encourages community-driven development, allowing developers to understand and influence the plugin's functionality. With the source code available, developers can now delve into the mechanics of Copilot's features like code completion and agentic workflows, fostering a collaborative environment for future enhancements.
GitHub Changelog