Models & Labs
llama.cpp b9010 Release Fixes CUDA Multi-GPU Issue
llama.cpp Releaseshigh confidence
Why it matters
- →Fixes critical multi-GPU support issue, enhancing performance for CUDA users.
- →Expands compatibility across various platforms, including Apple Silicon and Vulkan.
- →Improves stability and reliability of llama.cpp for diverse hardware setups.
The b9010 release of llama.cpp resolves a significant issue with CUDA device PCI bus ID detection that led to out-of-memory errors by ignoring additional GPUs. This fix enhances multi-GPU support, particularly benefiting users on Windows platforms. The update also includes platform-specific improvements for macOS, Linux, and Windows, with notable support for Apple Silicon and Vulkan. This release focuses on improving stability and compatibility rather than introducing new features.
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 b9056 Release Expands Platform Support
llama.cpp Releases · May 8, 2026 · Same story
- 2llama.cpp b9105 Release Enhances CUDA Integration
llama.cpp Releases · May 12, 2026 · Same story
Follow this story
Open the full 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.
