Open Source
Llama.cpp b9979 Release Fixes Prompt Truncation
llama.cpp Releaseshigh confidence
Why it matters
- →Fixes a critical bug affecting prompt integrity during tokenization.
- →Enhances reliability for developers using llama.cpp across different platforms.
- →Ensures consistent performance without unexpected data loss.
Llama.cpp has released version b9979, which fixes a significant issue where prompts were silently truncated due to embedded NUL bytes. This update ensures that message content is fully preserved during tokenization, preventing unexpected data loss. The release includes builds for multiple platforms, including macOS, Linux, Windows, and openEuler, but does not introduce new features. This update primarily enhances the reliability and compatibility of llama.cpp across various hardware setups.
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 b9169 Release Enhances Compatibility
llama.cpp Releases · May 16, 2026 · Same story
- 2llama.cpp b9950 release focuses on platform fixes
llama.cpp Releases · July 11, 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.
