Open Source
llama.cpp b9129 Release Enhances CPU Fallback
llama.cpp Releaseshigh confidence
Why it matters
- →Adaptive fallback improves performance for small batch sizes by using the CPU.
- →Developers gain more control over processing behavior with a new environment variable.
- →The update enhances compatibility across multiple platforms, supporting diverse hardware.
The b9129 release of llama.cpp brings an adaptive fallback feature to the ggml-zendnn backend, which defaults to the CPU for small batch sizes to enhance performance. This update is enabled by default and can be controlled via a new runtime environment variable. The release supports a wide array of platforms, including macOS, Windows, and Linux, ensuring broad compatibility. This development is aimed at optimizing processing efficiency across different hardware setups.
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.
