llama.cpp · b11919

opencl: refine mul mat id -1 index (#31170) Assisted-by: Codex **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11919/llama-b11919-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/b11919/llama-b11919-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11919/llama-b11919-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11919/llama-b11919-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11

1 个独立来源 · 1 篇报道切换最早在前 ↕

2026-10-27

llama.cpp releases15:42

b11919

opencl：优化矩阵乘法的ID-1索引（#31170）由Codex协助 **网站：** - **证明材料：** - **macOS/iOS：** - [macOS Apple Silicon（arm64）](https://github.com/ggml-org/llama.cpp/releases/download/b11919/llama-b11919-bin-macos-arm64.tar.gz) - macOS Apple Silicon（arm64，已启用KleidiAI）[已禁用](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel（x64）](https://github.com/ggml-org/llama.cpp/releases/download/b11919/llama-b11919-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11919/llama-b11919-xcframework.zip) **Linux：** - [Ubuntu x64（CPU）](https://github.com/ggml-org/llama.cpp/releases/download/b11919/llama-b11919-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64（CPU）](https://github.com/ggml-org/llama.cpp/releases/download/b11)

事件进展与其他报道