Models & Labs
llama.cpp b10172 Release Fixes and Enhancements
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances compatibility across multiple architectures, making the framework more versatile.
- →Fixes critical bugs that could affect performance and reliability.
- →Improves testing and diagnostics, particularly for Apple environments.
The latest b10172 release of llama.cpp introduces several fixes and enhancements aimed at improving compatibility and performance across multiple architectures. Key updates include resolving binding alias issues and fixing bugs related to buffer and view offsets. The release also enhances testing and diagnostics, particularly for Apple CI environments. This update does not introduce new models but focuses on strengthening the existing framework for 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.
How we got here
- 1llama.cpp b9724 Release with Bug Fixes
llama.cpp Releases · June 20, 2026 · Same story
- 2llama.cpp b9753 Release Fixes and Enhancements
llama.cpp Releases · June 22, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b11532 adds ModernBERT and CUDA 13
This release quietly fixes a critical accuracy gap for ModernBERT encoders by implementing exact GELU activation, ensuring semantic embeddings match the original PyTorch models rather than approximations. It also brings native support for CUDA 13.4 across Linux and Windows, closing the driver compatibility lag that has plagued NVIDIA users on newer hardware stacks. While KleidiAI builds are temporarily disabled on Apple Silicon, the broader expansion to ROCm 10.0 and Snapdragon NPU keeps llama.cpp as the most versatile local inference runtime available today.
llama.cpp Releases
Coding Toolscoding
llama.cpp b11533 fixes Adreno A6X crashes
This release targets a specific but painful stability issue for Android users running llama.cpp on Qualcomm Adreno A6X GPUs. The kernel compiler was crashing due to argument limits in the iot device backend, effectively breaking local inference on those chips. By skipping the problematic kernel and adding explicit detection for the Adreno 623, the team restores functionality where it previously failed hard. It’s a narrow fix, but essential for anyone trying to run models on mid-range Android hardware without hitting compiler errors.
