Models & Labs
Llama.cpp b9109 Release Enhances Drafting Support
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances parallel drafting, improving model processing efficiency.
- →Supports multiple speculative types, optimizing token acceptance.
- →Expands platform compatibility, increasing accessibility for developers.
Llama.cpp has released its b9109 update, focusing on enhancing parallel drafting support and refining speculative contexts. This update allows for multiple speculative types, improving the efficiency of token acceptance and drafting processes. The release also ensures compatibility across a wide range of platforms, including macOS, Linux, and Windows. While the update doesn't introduce new model architectures, it strengthens llama.cpp's existing capabilities, making it a more reliable tool for AI developers.
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 b9186 Release Expands Platform Support
llama.cpp Releases · May 17, 2026 · Same story
- 2llama.cpp b9219 Release Expands Platform Support
llama.cpp Releases · May 19, 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.
