Models & Labs
llama.cpp b10064 Release Expands Platform Support
llama.cpp Releaseshigh confidence
Why it matters
- →Expands GPU support with Vulkan and ROCm 7.2, enhancing performance options.
- →Increases compatibility across a wide range of hardware, making it more versatile.
- →Continues to position llama.cpp as a leading inference runtime for diverse systems.
The b10064 release of llama.cpp has been announced, featuring expanded support across multiple platforms. This update includes Vulkan support for both Ubuntu and Windows, and ROCm 7.2 for Ubuntu, enhancing GPU capabilities. Although KleidiAI support is disabled for macOS Apple Silicon, the release still covers a broad spectrum of architectures. This positions llama.cpp as a flexible tool for developers working with diverse hardware setups.
Read originalMore from llama.cpp Releases
Open Sourcemodels
llama.cpp b10056 Release Expands Platform Support
The b10056 release of llama.cpp continues its trend of broadening platform compatibility, making it a versatile tool for developers across various systems. Notably, this update includes support for Ubuntu with ROCm 7.2, enhancing performance for AMD GPU users. The release also maintains its commitment to diverse hardware by supporting both Intel and Apple Silicon on macOS, as well as Vulkan and OpenVINO on Windows. While no groundbreaking new features are introduced, the steady expansion of supported environments ensures that llama.cpp remains a go-to choice for developers seeking flexibility in AI model deployment.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10057 release focuses on SYCL fixes
The b10057 release of llama.cpp targets critical SYCL-related issues, enhancing the stability of its computation kernels. A significant fix addresses a row calculation error when K_QUANTS_PER_ITERATION is set to 1, ensuring more accurate results. Additionally, the update corrects the processing of reordered q5_k kernels, which is crucial for maintaining performance integrity. These improvements, contributed by Intel's Todd Malsbary, are designed to bolster the accuracy and efficiency of SYCL operations. While no new features are introduced, the release strengthens the existing framework, providing developers with a more reliable environment for SYCL-based computations.
llama.cpp Releases
Open Sourcecoding
llama.cpp b10058 release enhances Vulkan support
The b10058 release of llama.cpp marks a notable step forward with the addition of Vulkan Q2_0, significantly boosting performance for matrix-vector multiplication tasks. By optimizing the rows per workgroup, the update addresses initial inefficiencies, leading to improved computational efficiency. The release also tackles merge conflicts and fine-tunes error thresholds for specific operations. While it doesn't introduce new model architectures, this update strengthens llama.cpp's role as a robust tool for developers across platforms like macOS, Linux, Windows, and openEuler. The inclusion of ROCm 7.2 and CUDA 12 and 13 builds further broadens its applicability, making it a more versatile choice for diverse development environments.
llama.cpp Releases
More in Models & Labs
© TechCrunch AIModels & Labsmodels
Moonshot AI's Kimi K3 Sparks Global AI Debate
The release of Moonshot AI's Kimi K3 model has intensified discussions about the impact of open source AI on global competition. Although Kimi K3 doesn't yet match the capabilities of leading proprietary models like Claude Fable 5, its strong performance has raised concerns about China's expanding role in AI development. This launch, coinciding with President Xi Jinping's speech, led to a market reaction with Nasdaq dropping as investors considered the geopolitical stakes. The situation brings to the forefront the ongoing tension between fostering innovation through open source models and the need for regulatory oversight in the AI sector.
TechCrunch AI
© Lev SelectorModels & Labsmodels
PrismML Runs 27B-Parameter Model on iPhone
PrismML has successfully run a 27 billion parameter model on an iPhone, showcasing mobile AI capabilities.
Lev Selector
© Lev SelectorModels & Labsmodels
Vulkan and Mojo Challenge Nvidia CUDA
Vulkan and Mojo are emerging as competitors to Nvidia CUDA, enabling LLMs to run efficiently on diverse hardware.
Lev Selector