b10425
ggml-org/llama.cppb10425Aug 14, 2026by github-actions[bot]
AI Summary
SYCL backend performance is improved by fusing the gated-delta-net state writeback Copy operation.
Key Highlights
- SYCL: Fuse gated-delta-net state writeback Copy
- Performance gains of approximately +1.2% on Arc Pro B70
- Standard builds for all supported platforms
New Features
- SYCL state writeback fusion optimization
Full Release Notes
<details open> sycl: fuse the gated-delta-net state writeback cpy (#26643) Port of https://github.com/ggml-org/llama.cpp/pull/23940. Arc Pro B70, Qwen 3.6 27B Q4_K - Medium (48 of its 64 blocks run gated_delta_net), -ngl 99 -fa 1 -ctk f16 -ctv f16 -b 2048 -ub 2048, interleaved A/B passes of r=3: tg128 23.91 / 23.90 / 23.90 -> 24.19 / 24.17 / 24.20 +1.2% tg128 (rebuild) 23.81 / 23.81 -> 24.09 / 24.10 +1.2% pp2048 1050.8 / 1053.9 -> 1053.8 / 1054.5 flat 2 seqs, tg128 32.73 / 32.75 -> 33.11 / 33.10 +1.1% </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-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/b10425/llama-b10425-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-ubuntu-vulkan-arm64.tar.gz) - Ubuntu x64 (ROCm 7.14)[DISABLED](https://github.com/ggml-org/llama.cpp/pull/26969) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-ubuntu-openvino-2026.2.1-x64.tar.gz) - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-ubuntu-sycl-fp32-x64.tar.gz) - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-ubuntu-sycl-fp16-x64.tar.gz) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-android-arm64.tar.gz) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-win-cpu-arm64.zip) - [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-win-opencl-adreno-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10425/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10425/cudart-llama-bin-win-cuda-13.3-x64.zip) - [Windows arm64 (CUDA 13) (preview)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-win-cuda-13.4-arm64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b10425/cudart-llama-bin-win-cuda-13.4-arm64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-win-vulkan-x64.zip) - [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-win-openvino-2026.2.1-x64.zip) - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-bin-win-sycl-x64.zip) - [Windows x64 (ROCm 7.14)](https://github.com/ggml-org/llama.cpp/releases/download/b10425/llama-b10425-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/b10425/llama-b10425-ui.tar.gz)