Models & Labs
llama.cpp b11155 adds ROCm 10 and CUDA 13 support
llama.cpp Releaseshigh confidence
Why it matters
- →Enables immediate use of llama.cpp on systems with CUDA 13 or ROCm 10 GPUs.
- →Provides precompiled binaries for Snapdragon AI hardware, expanding mobile edge options.
- →Disables KleidiAI on Apple Silicon to prevent potential stability issues in production.
llama.cpp has released build b11155, updating its precompiled binaries to support CUDA 13.4 and ROCm 10.0 across Linux and Windows platforms. The release also includes builds for Ubuntu arm64 with CUDA 13 and Snapdragon AI hardware. Notably, KleidiAI support on macOS Apple Silicon has been disabled in this version. This update ensures compatibility with the latest GPU drivers and accelerators for local LLM inference.
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 b11055 adds CUDA 13 and ROCm 10 builds
llama.cpp Releases · September 20, 2026 · Same story
- 2llama.cpp b11050 adds CUDA 13 and ROCm 10.0 support
llama.cpp Releases · September 20, 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.
