运行提示：已杀死！
请问一下，会是rknn-toolkit-lite2版本原因导致的吗？运行具体输出如下：
Initializing ONNX Runtime for vision encoder...
W rknn-toolkit-lite2 version: 2.1.0
I RKNN: [11:10:47.855] RKNN Runtime Information, librknnrt version: 2.1.0 (967d001cc8@2024-08-07T19:28:19)
I RKNN: [11:10:47.856] RKNN Driver Information, version: 0.9.6
I RKNN: [11:10:47.867] RKNN Model Information, version: 6, toolkit version: 2.3.2(compiler version: 2.3.2 (e045de294f@2025-04-07T19:48:25)), target: RKNPU v2, target platform: rk3588, framework name: ONNX, framework layout: NCHW, model inference type: static_shape
W RKNN: [11:10:47.868] RKNN Model version: 2.3.2 not match with rknn runtime version: 2.1.0
W RKNN: [11:10:52.812] query RKNN_QUERY_INPUT_DYNAMIC_RANGE error, rknn model is static shape type, please export rknn with dynamic_shapes
W Query dynamic range failed. Ret code: RKNN_ERR_MODEL_INVALID. (If it is a static shape RKNN model, please ignore the above warning message.)
Vision encoder loaded successfully.
ONNX Input: pixel_values, ONNX Output: vision_features
Initializing RKLLM Runtime...
W rkllm: Warning: Your rknpu driver version is too low, please upgrade to 0.9.7
I rkllm: rkllm-runtime version: 1.2.1, rknpu driver version: 0.9.6, platform: RK3588
I rkllm: loading rkllm model from ./language_model_w8a8.rkllm
I rkllm: rkllm-toolkit version: 1.2.1, max_context_limit: 4096, npu_core_num: 3, target_platform: RK3588, model_dtype: W8A8
I RKNN: [11:10:53.367] RKNN LLM Runtime Information, rknn llm lib version: 2.3.3b0 (60745f603@2025-06-18T12:21:09)
I RKNN: [11:10:53.367] RKNN Driver Information, version: 0.9.6
已杀死
你的系统内存够大吗？
你的系统内存够大吗？
感谢回复，可能是内存的问题，3588设备是8g内存，不确实运行时是否有足够多的内存空间。