Models & Labs
Llama.cpp b9442 Release Adds Jina Embeddings Support
llama.cpp Releaseshigh confidence
Why it matters
- →Adds support for Jina embeddings, enhancing language processing capabilities.
- →Expands platform compatibility, making it more versatile for developers.
- →Improves text processing accuracy with default lowercase setting.
Llama.cpp has released version b9442, which now supports Jina embeddings v2 base for Chinese, including a whitespace tokenizer. The update sets lowercase as the default, potentially improving text processing. The release includes builds for various platforms such as macOS, Linux, and Windows, though some features are disabled. This update enhances llama.cpp's capabilities, particularly for developers focusing on Chinese language 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.
What happened next
- 1Llama.cpp b9660 Release Fixes Parsing Issue
llama.cpp Releases · June 16, 2026 · Same story
- 2llama.cpp b10002 Release Expands Platform Support
llama.cpp Releases · July 15, 2026 · Same story
Follow this story
Open the full 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.
