llama.cpp ships b9690

▼ WHAT HAPPENED

llama.cpp cut release b9690 on 2026-06-17. Release notes excerpt: "metal : implement rope_back operator (#24725) Reuse existing rope kernels with a function constant to toggle forward/backward rotation, avoiding duplicate kernel code. Assisted-by: pi:llama.cpp/Qwen3.6-27B **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9690/llama-b9690-bin-macos-arm64.tar.gz) - macOS A..."

▼ 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/b9690[GITHUB-RELEASE]

[pulse item] · runlocalai.co/pulse/gh-ggml-org-llama-cpp-b9690