llama.cpp ships b9637

▼ WHAT HAPPENED

llama.cpp cut release b9637 on 2026-06-14. Release notes excerpt: "chat: add dedicated Cohere2MoE (North Code) parser (#24615) * chat: add dedicated Cohere2MoE (North Code) parser * Some renames to make @CISC happy :> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9637/llama-b9637-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](ht..."

▼ 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/b9637[GITHUB-RELEASE]

[pulse item] · runlocalai.co/pulse/gh-ggml-org-llama-cpp-b9637