llama.cpp 发布: b11044
来源摘要
hexagon: im2col update (#29103) * ggml-hexagon: accept 1D and padded IM2COL ops * ggml-hexagon: make pure-DDR IM2COL kernel is_2D-aware * ggml-hexagon: extend IM2COL DMA patch-embed fast path to 1D * ggml-hexagon: add blocked-staging general IM2COL DMA kernel **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11044/llama-b11044-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/b11044/llama-b11044-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11044/llama-b11044-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11044/llama-b11044-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11044/llama-b11044-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11044/llama-b11044-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11044/llama-b11044-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b11044/llama-b11044-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b11044/llama-b11044-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/b11044/cudart-llama-b11044-bin-ubuntu-cuda-12.8-x64.tar.gz) - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b11044/llama-b1104
阅读原始来源- 来源
- llama.cpp 发布 · 官方来源
- 来源发布
- 2026/09/19 05:52
- 来源更新
- 2026/09/19 05:55
- 首次采集
- 2026/09/19 12:56
本文为公开信息索引与摘要，详情及后续变化请以原始来源为准。