llama.cpp 发布: b11115

来源摘要

opencl: add bin kernel `kernel_gemm_noshuffle_q4_k_q8_1_dp4a_ila_a8_bin` (#29056) * opencl: add A8 Q4_K non-MoE dp4a binary kernel * opencl: rename binary kernel selection helpers **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11115/llama-b11115-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/b11115/llama-b11115-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11115/llama-b11115-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11115/llama-b11115-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11115/llama-b11115-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11115/llama-b11115-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11115/llama-b11115-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11115/llama-b11115-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11115/llama-b11115-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b11115/cudart-llama-b11115-bin-ubuntu-cuda-12.8-x64.tar.gz) - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11115/llama-b11115-bin-ubuntu-cuda-13.4-x64.tar.gz) - [CUDA 13.4 libraries](https://github.com/gg