AI 뉴스 · AI NEWS

llama.cpp · b11921

llama : remove obsolete n_pad from memory instances (#31200) Every caller passes n_pad = 1 and the only two users clamp it to 256. Drop the parameter, the members and the trivially true kv_size assert. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11921/llama-b11921-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/releases/download/b11921/llama-b11921-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11921/llama-b11921-xcfram

2026-10-27

llama.cpp releases16:01

b11921

llama : 메모리 인스턴스에서 더 이상 사용되지 않는 n_pad를 제거함 (#31200) 모든 호출자는 n_pad = 1을 전달하며, 유일한 두 사용자만 이를 256으로 클램프합니다. 해당 파라미터와 멤버들, 그리고 명백히 참인 kv_size 확인 문장을 삭제합니다. 지원: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) **웹사이트:** - **인증서:** - **macOS/iOS:** - [macOS 애플 실리콘(arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11921/llama-b11921-bin-macos-arm64.tar.gz) - macOS 애플 실리콘(arm64, KleidiAI 활성화) [비활성화](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS 인텔(x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11921/llama-b11921-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11921/llama-b11921-xcfram)

진행 상황 및 관련 보도