llama.cpp ships b9406

▼ WHAT HAPPENED

llama.cpp cut release b9406 on 2026-05-29. Release notes excerpt: "llama: add llm_graph_input_mtp (#23643) * llama: add llm_graph_input_mtp * rename input_mtp -> input_token_embd * add TODO about mtmd embedding * cont : clean-up --------- Co-authored-by: Georgi Gerganov **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9406/llama-b9406-bin-macos-arm64.tar.gz) - macOS..."

▼ 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/b9406[GITHUB-RELEASE]

[pulse item] · runlocalai.co/pulse/gh-ggml-org-llama-cpp-b9406