llama.cpp ships b9650

▼ WHAT HAPPENED

llama.cpp cut release b9650 on 2026-06-15. Release notes excerpt: "sycl: fix soft_max_f32 max reduction (#24451) **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9650/llama-b9650-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/..."

▼ 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/b9650[GITHUB-RELEASE]

[pulse item] · runlocalai.co/pulse/gh-ggml-org-llama-cpp-b9650