llama.cpp ships b9680

▼ WHAT HAPPENED

llama.cpp cut release b9680 on 2026-06-17. Release notes excerpt: "ci: fix vulkan docker images (#24595) * Update vulkan-shaders-gen.cpp * Update vulkan-shaders-gen.cpp add comment describing code change intention * Update vulkan-shaders-gen.cpp fix potential UB **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9680/llama-b9680-bin-macos-arm64.tar.gz) - macOS Apple Silic..."

▼ 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/b9680[GITHUB-RELEASE]

[pulse item] · runlocalai.co/pulse/gh-ggml-org-llama-cpp-b9680