Models & Labs
llama.cpp b10355 Release Enhances Backend Sampling
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances backend sampling with multi-output capabilities, improving flexibility for developers.
- →Aligns CPU and GPU distributions, ensuring consistent performance across different hardware.
- →Fixes and improvements increase the reliability and robustness of llama.cpp.
The b10355 release of llama.cpp brings notable enhancements to backend sampling, including support for multi-output capabilities. This update ensures better alignment between CPU and GPU distributions and clamps the mask sum for more accurate sampling. It also addresses mismatches and fixes in CPU and Vulkan tests, improving the system's reliability. These improvements make llama.cpp a more robust tool for developers working across various hardware platforms.
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 b10412 Release Enhances Backend Sampling
llama.cpp Releases · August 14, 2026 · Same story
- 2llama.cpp b10982 Release Adds Vulkan Support
llama.cpp Releases · September 16, 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.
