Models & Labs
llama.cpp b10813 Release Enhances OpenCL Support
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances performance for devices using Adreno GPUs with optimized memory paths.
- →Expands compatibility with various hardware configurations, including Vulkan and ROCm support.
- →Incremental improvements increase the versatility of llama.cpp for developers.
The b10813 release of llama.cpp brings notable improvements to OpenCL support, specifically adding the Adreno xmem SDPA path. This enhancement, developed with the assistance of OpenAI Codex, is designed to optimize performance on devices with Adreno GPUs. The update also includes various platform-specific enhancements, such as Vulkan and ROCm support on Ubuntu, and CUDA support on Windows. These changes aim to make llama.cpp more adaptable and efficient across different 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 b9142 Release Expands OpenCL Support
llama.cpp Releases · May 14, 2026 · Same story
- 2llama.cpp b9852 release expands OpenCL support
llama.cpp Releases · July 2, 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.
