llama.cpp ships b9660

▼ WHAT HAPPENED

llama.cpp cut release b9660 on 2026-06-15. Release notes excerpt: "chat : fix LFM2 tool-call parsing double-escaping (#24667) * Add escape test cases * chat : fix LFM2 tool-call parsing double-escaping **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9660/llama-b9660-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/gg..."

▼ OPERATOR ANGLE

Read the release notes and decide whether operators need to act. test throughput and memory fit before pinning the new version. Publish if this changes model compatibility, GPU backend behavior, memory use, quantization paths, security posture, migration requirements, or production serving reliability.

SOURCE: https://github.com/ggml-org/llama.cpp/releases/tag/b9660[GITHUB-RELEASE]

[pulse item] · runlocalai.co/pulse/gh-ggml-org-llama-cpp-b9660