Models & Labs
Llama.cpp b10098 Release Enhances Hexagon Ops
llama.cpp Releaseshigh confidence
Why it matters
- →Enhancements improve computational efficiency for AI inference tasks.
- →Optimizations support a wide range of hardware configurations.
- →Focus on performance makes llama.cpp a more robust tool for developers.
Llama.cpp has released its b10098 update, focusing on improvements to Hexagon activation operations. The update includes optimized microkernels for geglu operations and enhancements for non-contiguous source and strided DMA. These changes aim to boost performance and efficiency across supported platforms, including macOS, Linux, Windows, and openEuler. While the release does not introduce new features, it enhances the existing framework, making it more efficient for developers working with AI inference tasks.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Llama.cpp b9784 Release Enhances Hexagon Performance
llama.cpp Releases · June 26, 2026 · Same story
- 2Llama.cpp b9946 Release Enhances Hexagon Optimizations
llama.cpp Releases · July 11, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
