Models & Labs
llama.cpp b11149 adds backend testing and ROCm 10 support
llama.cpp Releaseshigh confidence
Why it matters
- →ROCm 10.0 support officially brings first-class AMD GPU compatibility to the standard build pipeline.
- →CUDA 13.4 inclusion ensures forward compatibility with the latest NVIDIA driver releases.
- →New backend testing infrastructure reduces maintenance burden and improves reliability for diverse hardware setups.
llama.cpp has released version b11149, introducing explicit support for ROCm 10.0 and CUDA 13.4 across Linux and Windows platforms. The update also implements a new backend testing option (-b/--backend) to validate specific hardware configurations more rigorously. Supported architectures now include AMD GPUs via ROCm, NVIDIA GPUs with the latest CUDA versions, and various CPU backends including Apple Silicon and Intel. This release focuses on infrastructure stability and broader hardware compatibility rather than new model 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.
How we got here
- 1llama.cpp b11080 release with ROCm 10 and CUDA 13
llama.cpp Releases · September 22, 2026 · Same story
What happened next
- 2llama.cpp b12054 adds CUDA 13 and ROCm 10.0
llama.cpp Releases · November 3, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12336 fixes HunyuanVL crash
This release quietly patches a critical memory overflow in the mtmd module that caused crashes when loading HunyuanVL models. The issue stemmed from F64 position embeddings overflowing an F32 buffer, a subtle bug that broke multimodal inference for users relying on this specific architecture. By enforcing strict F32 requirements, llama.cpp stabilizes support for Tencent's vision-language model without adding new features or changing the core API. It’s a necessary maintenance update that keeps local multimodal workflows from breaking unexpectedly.
llama.cpp Releases
Models & Labsother
llama.cpp b12340 adds CUDA 13 and ROCm 10.0
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13 and ROCm 10.0 across Linux and Windows. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get performance, while Apple Silicon builds now ship KleidiAI disabled by default, shifting the focus back to standard ARM optimizations. The inclusion of Snapdragon support for Linux and Android marks a significant step toward on-device AI beyond the x86/ARM desktop ecosystem. It is less about new features and more about ensuring llama.cpp remains the universal runtime for every available accelerator.
