b10726

<details open>

AVX2: Speed up large batch size prompt processing of IQ models (#27402)

* Batched gemm for grid IQ quants

Style updates and a bit more performance

Clean up comments

Move code around

Vectorize IQ panel decode, lower threshold for speedup

IQ panel: single-source gather layout, gate bias, vectorize interleave

Add ggml_gemm_iqp_8x8_q8_K_p4 kernel, remove gather buffer

Move IQ panel code out of repack into iqp.cpp, clean up comments

Another comment sweep

* Add myself as iqp.* codeownder

* Remove ggml_cpu_iqp_scratch_offset and ggml_cpu_iqp_src1_conv_size

* Renaming and moving

* The other half of renaming and moving

* Move macros and ggml_cpu_iqp_mul_mat_id_min_batch definition

* Update ggml/src/ggml-cpu/iqp.h

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Add iqp_rows work buffer

* Revert "Add iqp_rows work buffer"

This reverts commit 425542991eee1b01fa3844bf87fc4f205ddbfccb.

* Add NUMA fallback

* Add 10 row batch tests for IQP coverage on all grid IQ types

* Swap assert for return false in support check

* Move IQP mul_mat_id test

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

</details>

**Website:**
- <https://llama.app>

**Attestations:**
- <https://github.com/ggml-org/llama.cpp/attestations/44236891>

**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-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/b10726/llama-b10726-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-xcframework.zip)

**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-ubuntu-arm64.tar.gz)
- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-ubuntu-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (ROCm 7.14)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-ubuntu-rocm-7.14-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-ubuntu-openvino-2026.3.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-ubuntu-sycl-fp16-x64.tar.gz)

**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-android-arm64.tar.gz)

**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10726/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10726/cudart-llama-bin-win-cuda-13.3-x64.zip)
- [Windows arm64 (CUDA 13) (preview)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-cuda-13.4-arm64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10726/cudart-llama-bin-win-cuda-13.4-arm64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-vulkan-x64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-openvino-2026.3.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-sycl-x64.zip)
- [Windows x64 (ROCm 7.14)](https://github.com/ggml-org/llama.cpp/releases/download/b10726/llama-b10726-bin-win-rocm-7.14-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/b10726/llama-b10726-ui.tar.gz)