Models & Labs
llama.cpp b9100 Release Expands Sampling Support
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances the accuracy of AI model sampling by ensuring non-zero probabilities.
- →Expands platform support, making llama.cpp more accessible to developers.
- →Strengthens llama.cpp's position as a versatile tool for AI development.
The b9100 release of llama.cpp focuses on backend sampling improvements, notably supporting the return of post-sampling probabilities. This ensures that probabilities are not returned as zero, enhancing the accuracy of sampling results. The update also extends platform compatibility, covering macOS, Linux, Windows, and Android, with specific support for technologies like Vulkan and ROCm. This release is a step forward in making llama.cpp a more robust and reliable tool for developers working with AI 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 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.
