llama.cpp ships b9647

▼ WHAT HAPPENED

llama.cpp cut release b9647 on 2026-06-15. Release notes excerpt: "[SYCL] add to support pool_1d, move pool_1d/2d code to pool.cpp/hpp (#24584) * add to support pool_1d, move pool_1d/2d code to pool.cpp/hpp * update ops.md **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9647/llama-b9647-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](..."

▼ 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/b9647[GITHUB-RELEASE]

[pulse item] · runlocalai.co/pulse/gh-ggml-org-llama-cpp-b9647