llama.cpp cut release b9515 on 2026-06-04. Release notes excerpt: "Move duplicated imatrix code into single common imatrix-loader.cpp (#22445) * Deduplicate imatrix loading code * Add back LLAMA_TRACE, early exit on quantize missing metadata **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9515/llama-b9515-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI e..."
▼ 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.