Update:

ggerganov/llama.cpp b9213: b9213

GitHub·AI·Silent·5/18/2026

<details open> llama: initialize pre-norm embedding mask flag (#23256) </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9213/llama-b9213-bin-macos-arm64.tar.gz) - [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/g

Why it matters → llama.cpp released an update. Review the changelog for relevant changes.

Who should care → Teams using llama.cpp.

llama.cpp

View original source ↗

Source payload preview

{
  "id": 324456162,
  "url": "https://api.github.com/repos/ggml-org/llama.cpp/releases/324456162",
  "body": "<details open>\n\nllama: initialize pre-norm embedding mask flag (#23256)\n\n</details>\n\n**macOS/iOS:**\n- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9213/llama-b9213-bin-macos-arm64.tar.gz)\n- [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download/b9213/llama-b9213-bin-macos-arm64-kleidiai.tar.gz)\n- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b9213/llama-b9213-bin-macos-x64.tar.gz)\n- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9213/llama-b9213-xcframework.zip)\n\n**Linux:**\n- [Ubuntu x64 (CPU)](https://github.com/ggml-org
…