Models & Labs
llama.cpp b11849 adds Hexagon SGN op
llama.cpp Releaseshigh confidence
Why it matters
- →Hexagon NPU support expands local inference options for Snapdragon-based mobile and edge devices.
- →CUDA 13 and ROCm 10.0 builds ensure compatibility with the latest NVIDIA and AMD hardware drivers.
- →Optimized dimension collapsing improves efficiency for specific tensor operations on supported backends.
llama.cpp has released build b11849, introducing support for the Hexagon SGN operator to enhance performance on Qualcomm Snapdragon devices. The update includes optimized sign bit handling and improved dimension collapsing logic for the Hexagon NPU. Additionally, the release adds binaries for CUDA 13 (12.8/13.4 libraries) and ROCm 10.0 across Linux and Windows platforms. This maintains compatibility with the latest GPU driver ecosystems while expanding edge AI capabilities.
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 b11054 adds Hexagon TOP_K support
llama.cpp Releases · September 20, 2026 · Same story
- 2llama.cpp b11272 optimizes Hexagon NPU and adds CUDA 13
llama.cpp Releases · September 30, 2026 · Same story
Follow this story
Open the full story →llama.cpp b11680 Hexagon NPU and CUDA 13 support
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.
