Open Source
llama.cpp b9495 release enhances platform support
llama.cpp Releaseshigh confidence
Why it matters
- →The update improves model performance with post-norm hidden states.
- →Expanding platform support increases accessibility for developers.
- →Renaming conventions indicate structural changes in the framework.
The latest b9495 release of llama.cpp introduces several updates, including the use of post-norm hidden states for the qwen35 model's MTP. The release also renames 'pre_norm' to 'nextn', reflecting a change in the framework's structure. While some features are disabled, such as KleidiAI on macOS Apple Silicon, the update enhances support for platforms like Ubuntu with ROCm 7.2 and Windows with CUDA 12 and 13. These changes aim to improve the framework's adaptability and performance across different environments.
Read originalMore from llama.cpp Releases
Open Sourcemodels
llama.cpp b10952 Release Expands Platform Support
The b10952 release of llama.cpp continues its trend of broadening platform compatibility, now supporting a wide array of systems including macOS, Linux, Windows, and openEuler. Notably, this update includes support for Vulkan and ROCm 10.0 on Ubuntu, as well as CUDA 12 and 13 on Windows, enhancing its utility for developers working across diverse hardware configurations. While KleidiAI support on macOS Apple Silicon is disabled, the release still marks a significant step in making llama.cpp a versatile tool for AI inference across different environments. This update doesn't introduce new models but solidifies llama.cpp's position as a flexible runtime option for developers beyond the NVIDIA ecosystem.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
