llama.cpp 发布: b11173

来源摘要

metal : fix graph capture and handle empty graphs (#29390) - return early when the graph has no nodes - drop the redundant reset of capture_compute: the decrement at the top of the function already transitions the counter from 0 to -1, so a capture happens exactly once - hint at METAL_CAPTURE_ENABLED=1 in the capture error message - pass capture_compute == 0 (not the raw counter) as use_capture to ggml_metal_op_init, so GPU debug-group markers are only emitted on the captured compute Assisted-by: pi:llama.cpp/Qwen3.8-27B **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11173/llama-b11173-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/b11173/llama-b11173-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11173/llama-b11173-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11173/llama-b11173-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11173/llama-b11173-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11173/llama-b11173-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11173/llama-b11173-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11173/llama-b11173-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11173/llama-b11173-bin-u