llama.cpp 发布: b11111

来源摘要

vulkan: add Intel Xe flash attention optimization kernels (2/3, Xe-LPG Plus/Xe2/Xe3) (#24406) * vulkan : Intel FA kernel optimization for split k path * vulkan : Host code update for Intel split k FA kernel path selection, fix A770 Linux op test failures * vulkan : use symmetric coopMatMulAdd() in flash_attn_decode_phase_1 shader to resolve test op failre on A770 Linux with 26.2.3 mesa driver * vulkan : fix editorconfig issue in flash_attn_decode_phase_2.comp --------- Co-authored-by: Liu, Russell **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11111/llama-b11111-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/b11111/llama-b11111-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11111/llama-b11111-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11111/llama-b11111-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11111/llama-b11111-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11111/llama-b11111-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11111/llama-b11111-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11111/llama-b11111-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11111/llama-b11111-bin-ubuntu-cuda-12.8-x64.tar.