b12336

<details open> mtmd: require an F32 position embedding for HunyuanVL (#32131) HunyuanVL resamples its position embedding on the host into a float buffer sized for F32, then reads ggml_nbytes() of the tensor into it. The graph never uses the tensor, so any type loads, and an F64 tensor overflows the buffer at the first image request. Require the position embedding to be present and F32 when loading the HunyuanVL tensors. </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/66963761> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-arm64.tar.gz) - [Ubuntu 24.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-s390x.tar.gz) - [Ubuntu 26.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-26.04-s390x.tar.gz) - [Ubuntu 26.04 s390x (zDNN)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-zdnn-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12336/cudart-llama-b12336-bin-ubuntu-cuda-12.8-x64.tar.gz) - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-cuda-13.5-x64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12336/cudart-llama-b12336-bin-ubuntu-cuda-13.5-x64.tar.gz) - [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-cuda-13.5-arm64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12336/cudart-llama-b12336-bin-ubuntu-cuda-13.5-arm64.tar.gz) - [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-rocm-10.0-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-openvino-2026.4.1-x64.tar.gz) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-sycl-fp32-x64.tar.gz) - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-ubuntu-sycl-fp16-x64.tar.gz) - [Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-linux-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-android-arm64.tar.gz) - [Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-android-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-cpu-arm64.zip) - [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-opencl-adreno-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12336/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-cuda-13.5-x64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12336/cudart-llama-bin-win-cuda-13.5-x64.zip) - [Windows arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-cuda-13.5-arm64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12336/cudart-llama-bin-win-cuda-13.5-arm64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-vulkan-x64.zip) - [Windows arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-vulkan-arm64.zip) - [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-openvino-2026.4.1-x64.zip) - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-sycl-x64.zip) - [Windows x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-bin-win-rocm-10.0-x64.zip) **openEuler:** - [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) - openEuler x86 (310p) - openEuler x86 (910b, ACL Graph) - openEuler aarch64 (310p) - openEuler aarch64 (910b, ACL Graph) **UI:** - [UI](https://github.com/ggml-org/llama.cpp/releases/download/b12336/llama-b12336-ui.tar.gz)