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 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 b10105 Release Refines Argument Handling
llama.cpp Releases · July 25, 2026 · Same story
- 2llama.cpp b10441 Release Updates Load Mode
llama.cpp Releases · August 16, 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.
