MiniCPM-V 4.7 首日支持 AMD Radeon GPU、Ryzen AI 集成显卡和 Ryzen AI NPU，赋能端侧与边缘 AI

		rocminfo | grep -E 'Name:[[:space:]]+gfx' | sort -u
rocm-smi --showproductname --showmeminfo vram
	

		sudo apt-get update
sudo apt-get install -y build-essential cmake git
 
git init llama.cpp
cd llama.cpp
git remote add origin https://github.com/tc-mb/llama.cpp.git
git fetch --depth 1 origin 6b31908189524f2f98824a38e09a553ea43cbd21
git checkout --detach FETCH_HEAD
GPU_TARGET=gfx1201
BUILD_DIR="build-$GPU_TARGET"
HIPCXX="$(hipconfig -l)/clang" \
HIP_PATH="$(hipconfig -R)" \
cmake -S . -B "$BUILD_DIR" \
    -DGGML_HIP=ON \
    -DGPU_TARGETS="$GPU_TARGET" \
    -DGGML_NATIVE=OFF \
    -DLLAMA_CURL=OFF \
    -DLLAMA_BUILD_SERVER=ON \
    -DLLAMA_BUILD_TESTS=OFF \
    -DCMAKE_BUILD_TYPE=Release
 
cmake --build "$BUILD_DIR" \
    --target llama-mtmd-cli llama-server \
    --config Release \
    --parallel 16
	

		export MODEL_GGUF="/absolute/path/to/model.gguf"
export MMPROJ_GGUF="/absolute/path/to/matching-mmproj.gguf"
export IMAGE_FILE="/absolute/path/to/input.png"
	

		: "${MODEL_GGUF:?set MODEL_GGUF to the released language-model GGUF}"
: "${MMPROJ_GGUF:?set MMPROJ_GGUF to the matching visual projector}"
: "${IMAGE_FILE:?set IMAGE_FILE to an input image}"

BIN="$PWD/$BUILD_DIR/bin"
export LD_LIBRARY_PATH="$BIN${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
"$BIN/llama-mtmd-cli" \
        -m "$MODEL_GGUF" \
        --mmproj "$MMPROJ_GGUF" \
        --image "$IMAGE_FILE" \
        --prompt 'Please describe the main content of the image.' \
        --jinja \
        -c 4096 \
        -n 192 \
        --temp 0 \
        -ngl 999
	

		"$BIN/llama-server" \
    -m "$MODEL_GGUF" \
    --mmproj "$MMPROJ_GGUF" \
    --host 0.0.0.0 \
    --port 8080 \
    --jinja \
    -c 4096 \
    -np 1 \
    -ngl 999
	

		flm version
flm validate
	

		flm pull minicpm-v-4.7:1b
flm check minicpm-v-4.7:1b
	

		flm pull minicpm-v-4.7:1b --modelscope
	

		flm run minicpm-v-4.7:1b
/input C:\path\to\image.png Please describe the image.
	

		flm serve minicpm-v-4.7:1b
	

		import base64
import json
import urllib.request
 
image_path = r"C:\path\to\image.png"
with open(image_path, "rb") as f:
    image = base64.b64encode(f.read()).decode("ascii")
 
body = {
    "model": "minicpm-v-4.7:1b",
    "temperature": 0,
    "max_tokens": 256,
    "think": False,
    "messages": [{
        "role": "user",
        "content": [
            {"type": "text", "text": "Please describe the image."},
            {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{image}"}},
        ],
    }],
}
req = urllib.request.Request(
    "http://127.0.0.1:52625/v1/chat/completions",
    data=json.dumps(body).encode("utf-8"),
    headers={"Content-Type": "application/json"},
)
with urllib.request.urlopen(req, timeout=180) as resp:
    print(json.load(resp)["choices"][0]["message"]["content"])