Models & Labs
llama.cpp b10541 Release Adds New Features
llama.cpp Releaseshigh confidence
Why it matters
- →The new --mmproj-device argument enhances flexibility in device backend management.
- →Backwards compatibility ensures that existing workflows remain unaffected.
- →Streamlined backend loading improves efficiency for developers.
The b10541 release of llama.cpp brings new features aimed at improving developer experience. A notable addition is the --mmproj-device argument, which allows for more flexible device backend management. The update also includes a backwards-compatible environment variable and a shortflag for easier command-line access. These enhancements are designed to streamline the process of working with different device backends, making the tool more versatile for developers. This release focuses on refining existing capabilities rather than introducing new models.
Read originalMore from llama.cpp Releases
Models & Labsmodels
llama.cpp b10545 Release Fixes Tensor API Bug
The latest release of llama.cpp, version b10545, addresses a critical bug in the Tensor API's mat-mat kernel. Previously, the kernel could read out-of-bounds elements when the K dimension wasn't a multiple of 32, leading to potential data corruption or NaN results. This update introduces a dynamic extent for K, ensuring that only valid data is processed, thus enhancing the reliability of matrix operations. This fix is crucial for developers relying on precise tensor computations, especially in environments where K-aligned inputs are not guaranteed.
llama.cpp Releases
Open Sourcemodels
llama.cpp b10566 Release Expands Platform Support
The b10566 release of llama.cpp focuses on broadening its reach across various architectures, though it doesn't bring any groundbreaking innovations. This update includes support for macOS, Linux, Windows, and openEuler, with some configurations like macOS Apple Silicon with KleidiAI and Ubuntu x64 with ROCm 7.14 being disabled. The release ensures that llama.cpp remains a versatile tool, offering Vulkan and OpenVINO support on different systems. While it doesn't introduce new features, it solidifies llama.cpp's role as a flexible inference runtime, accommodating a wide array of hardware environments.
llama.cpp Releases
Open Sourcemodels
llama.cpp b10568 Release Expands Platform Support
The latest b10568 release of llama.cpp continues its trend of broadening platform compatibility, now incorporating the ggml_rope_set_offset() function. This update partially applies to deepseek2, enhancing its functionality. The release maintains support across a wide array of systems, including macOS, Linux, Windows, and openEuler, with specific configurations for Vulkan, ROCm, and CUDA environments. While no groundbreaking features are introduced, this update solidifies llama.cpp's position as a versatile tool for developers working across diverse hardware setups.
llama.cpp Releases
More in Models & Labs
Models & Labsmodels
v0.28.0rc2: DFlash2 Local Convolution Update
The v0.28.0rc2 release of vLLM introduces DFlash2, a feature that enhances local convolution capabilities with a candidate selector. This update, cherry-picked from a specific commit, signifies a technical refinement aimed at improving model performance. While the specifics of the implementation are technical, the focus on local convolution suggests a targeted improvement in processing efficiency. This release is a step forward for developers looking to optimize their AI models with more precise convolution operations.
vLLM Releases
© Lev SelectorModels & Labsmodels
Qwen3.8-27B Model Released with MTP for Faster Performance
The Qwen3.8-27B model has been released, featuring MTP technology for enhanced speed and local operation capabilities.
Lev Selector
© Lev SelectorModels & Labsmodels
GLM-5.3 Outperforms Mythos 5 in Cybersecurity
The open-source model GLM-5.3 has surpassed Mythos 5 in cybersecurity performance, showcasing advancements in Chinese AI models.
Lev Selector