Versions/bucket/llama.cpp-cpu.json

{
    "version": "b10176",
    "description": "Inference of LLaMA model in pure C/C++ (CPU version)",
    "homepage": "https://github.com/ggml-org/llama.cpp",
    "license": "MIT",
    "architecture": {
        "64bit": {
            "url": "https://github.com/ggml-org/llama.cpp/releases/download/b10176/llama-b10176-bin-win-cpu-x64.zip",
            "hash": "cf556f9c7e6c986961f96baf8067cd535c0574f1103b55e0f31fa3c7bfbf11ba"
        },
        "arm64": {
            "url": "https://github.com/ggml-org/llama.cpp/releases/download/b10176/llama-b10176-bin-win-cpu-arm64.zip",
            "hash": "67eba6ab7cd4b662e88cdea6740f37fc76603a7bb0c12f4599274507456e44de"
        }
    },
    "bin": [
        "llama-batched-bench.exe",
        "llama-bench.exe",
        "llama-cli.exe",
        "llama-completion.exe",
        "llama-fit-params.exe",
        "llama-gemma3-cli.exe",
        "llama-gguf-split.exe",
        "llama-imatrix.exe",
        "llama-llava-cli.exe",
        "llama-minicpmv-cli.exe",
        "llama-mtmd-cli.exe",
        "llama-perplexity.exe",
        "llama-quantize.exe",
        "llama-qwen2vl-cli.exe",
        "llama-server.exe",
        "llama-tokenize.exe",
        "llama-tts.exe"
    ],
    "persist": "models",
    "checkver": {
        "github": "https://github.com/ggml-org/llama.cpp",
        "regex": "(b[\\d]+)"
    },
    "autoupdate": {
        "architecture": {
            "64bit": {
                "url": "https://github.com/ggml-org/llama.cpp/releases/download/$version/llama-$version-bin-win-cpu-x64.zip"
            },
            "arm64": {
                "url": "https://github.com/ggml-org/llama.cpp/releases/download/$version/llama-$version-bin-win-cpu-arm64.zip"
            }
        }
    }
}