Models & Labs
llama.cpp b9568 Release Enhances Model Support
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances model versatility with support for new assistants.
- →Streamlines conversion processes by removing debug features.
- →Expands platform compatibility, particularly on Ubuntu.
The b9568 release of llama.cpp brings new support for gemma-4 E2B and E4B assistants, enhancing the model's adaptability. Key updates include the addition of masked_embd tensors to the gemma4-assist architecture and the removal of temporary debug features to streamline conversions. The release maintains broad platform support, with notable compatibility for Vulkan and ROCm 7.2 on Ubuntu. While some features remain disabled, this update reflects llama.cpp's focus on improving model conversion processes.
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.
What happened next
- 1llama.cpp b9653 Release Expands Platform Support
llama.cpp Releases · June 16, 2026 · Same story
- 2llama.cpp b10444 Release Expands Model Support
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.
