b12189

<details open> metal : fix GROUP_NORM for ne03 > 1 and non-contiguous inputs (#31852) The kernel_group_norm_f32 kernel and its host dispatch ignored the batch dimension (ne03) of the source tensor: only ngrp threadgroups were dispatched and each normalized the flat range [tgpig*gs, (tgpig+1)*gs) with gs = ne00*ne01*ceil(ne02/ngrp). For tensors with ne03 > 1, all but the first ne00*ne01*ne02 elements were left unwritten (exposed by the new GROUP_NORM test with ne=[3,1,1,65537], num_groups=1). Dispatch one threadgroup per (group, i03) pair (ngrp in x, ne03 in z, same work distribution as the Vulkan backend) and compute per-batch statistics, matching the CPU reference. Also clamp the group element count for the last group when ne02 is not divisible by ngrp and use int64_t indexing. The kernel now only requires ggml_is_contiguous_rows(op->src[0]) instead of full contiguity: it addresses src0 and dst with their own strides (nb03 and the dst strides are added to the kernel args - dst can be a strided view of src0 with ggml_group_norm_inplace) and falls back from the flat fast path to a strided path that decodes the linear element index when rows or channels are padded. The flat/strided selection is done on the host in ggml_metal_library_get_pipeline_group_norm and compiled into one of two specialized pipeline variants via a FC_group_norm_flat function constant, so the dead path is eliminated at pipeline creation. GROUP_NORM support is also gated on F32 src and dst in supports_op - the kernel only implements f32 and an f16 input would silently be read as f32. Assisted-by: dsh:llama.cpp/ggml-org/GLM-5.3-Flash-GGUF (Mac Studio, M5 Ultra, 256GB) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/64836151> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-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/b12189/llama-b12189-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-s390x.tar.gz) - [Ubuntu 26.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-26.04-s390x.tar.gz) - [Ubuntu 26.04 s390x (zDNN)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-zdnn-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12189/cudart-llama-b12189-bin-ubuntu-cuda-12.8-x64.tar.gz) - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-cuda-13.5-x64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12189/cudart-llama-b12189-bin-ubuntu-cuda-13.5-x64.tar.gz) - [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-cuda-13.5-arm64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b12189/cudart-llama-b12189-bin-ubuntu-cuda-13.5-arm64.tar.gz) - [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-rocm-10.0-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-openvino-2026.4.1-x64.tar.gz) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-sycl-fp32-x64.tar.gz) - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-ubuntu-sycl-fp16-x64.tar.gz) - [Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-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/b12189/llama-b12189-bin-android-arm64.tar.gz) - [Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-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/b12189/llama-b12189-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-win-cpu-arm64.zip) - [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-win-opencl-adreno-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12189/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-win-cuda-13.5-x64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12189/cudart-llama-bin-win-cuda-13.5-x64.zip) - [Windows arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-win-cuda-13.5-arm64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b12189/cudart-llama-bin-win-cuda-13.5-arm64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-win-vulkan-x64.zip) - [Windows arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-win-vulkan-arm64.zip) - [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-win-openvino-2026.4.1-x64.zip) - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-bin-win-sycl-x64.zip) - [Windows x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b12189/llama-b12189-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/b12189/llama-b12189-ui.tar.gz)