ggerganov/llama.cpp b9519: b9519
retained text
<details open> sycl : port multi-column MMVQ from CUDA backend (#21845) mmvq: Port the ncols_dst optimization from ggml-cuda/mmvq.cu to SYCL. Read weights once per dispatch instead of once per column. Covers all standard quant types + reorder paths for Q4_0, Q8_0, Q3_K, Q4_K, Q5_K, Q6_K. IQ types (except IQ4_XS) excluded due to incompatible vec_dot signatures. ggml-sycl: The weight reorder was only bootstrapped on single-token mat-vec (ne[1] == 1). Speculative / MTP verify issues only multi-column mat-vec, so it never triggered the reorder and ran on the slower non-reorder kernel. Bootstrap it on small multi-column batches (ne[1] <= 8) too. </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-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/b9519/llama-b9519-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-ubuntu-rocm-7.2-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-ubuntu-openvino-2026.0-x64.tar.gz) - Ubuntu x64 (SYCL FP32) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-android-arm64.tar.gz) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-win-cpu-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9519/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9519/cudart-llama-bin-win-cuda-13.3-x64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-win-vulkan-x64.zip) - Windows x64 (SYCL) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) - [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9519/llama-b9519-bin-win-hip-radeon-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/b9519/llama-b9519-ui.tar.gz)
document fetched 2026-06-05 09:36