llama-quant : fix 4D tensor quantization using ggml_nrows() and name-based expert detection (#30820)
* llama-quant : fix quantizing 4D tensors
nrows_total was ne[1]*ne[2], so for a 4D tensor only the first ne[2]
slices were quantized and the rest of the rows were dropped. Use
ggml_nrows(tensor) to count all rows, including ne[3].
Fixes #29916
* llama-quant : detect expert tensors by name and fix imatrix size for 4D tensors
The MXFP4_MOE path used ne[2] > 1 to detect MoE expert tensors. This is
wrong for non-expert tensors with 3 or more dims, e.g. MLA projections
(BailingMoE3) and 4D conv kernels. Use the tensor name instead: all
tensors used by GGML_OP_MUL_MAT_ID are named *_exps or *_chexps. This
also removes the BailingMoE3 special case.
The imatrix holds one vector of ne[0] values per 2D slice, so the
expected size is ne[0]*ne[2]*ne[3], not ne[0]*ne[2]. This matches how
the imatrix is indexed per row for 4D tensors in llama_tensor_quantize_impl.
Assisted-by: Claude Opus 5.5
**Website:**
-
**Attestations:**
-
**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-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/b11883/llama-b11883-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-xcframework.zip)
**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b11883/cudart-llama-b11883-bin-ubuntu-cuda-12.8-x64.tar.gz)
- [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-cuda-13.4-x64.tar.gz) - [CUDA 13.4 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b11883/cudart-llama-b11883-bin-ubuntu-cuda-13.4-x64.tar.gz)
- [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-cuda-13.4-arm64.tar.gz) - [CUDA 13.4 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b11883/cudart-llama-b11883-bin-ubuntu-cuda-13.4-arm64.tar.gz)
- [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-rocm-10.0-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-openvino-2026.4.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-ubuntu-sycl-fp16-x64.tar.gz)
- [Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-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/b11883/llama-b11883-bin-android-arm64.tar.gz)
- [Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-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/b11883/llama-b11883-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b11883/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-win-cuda-13.4-x64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b11883/cudart-llama-bin-win-cuda-13.4-x64.zip)
- [Windows arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-win-cuda-13.4-arm64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b11883/cudart-llama-bin-win-cuda-13.4-arm64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-win-vulkan-x64.zip)
- [Windows arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-win-vulkan-arm64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-win-openvino-2026.4.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-bin-win-sycl-x64.zip)
- [Windows x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/b11883/llama-b11883-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/b11883/llama-b11883-ui.tar.gz)