RK3588运行一直挂起
请问在RK3588运行一直挂起，Received ready signal: vision_ready等了几分钟都没有往下执行，是什么原因？
(rknn) root@ai:/srv/src/MiniCPM-V-2_6-rkllm# taskset -c 4-7 python multiprocess_inference.py
Start loading language model (size: 7810.02 MB)
I rkllm: rkllm-runtime version: 1.1.2, rknpu driver version: 0.9.8, platform: RK3588
W rknn-toolkit-lite2 version: 2.3.0
Start loading vision encoder model (size: 942.29 MB)
Vision encoder loaded in 4.31 seconds
I RKNN: [10:37:07.385] RKNN Runtime Information, librknnrt version: 2.3.0 (c949ad889d@2024-11-07T11:35:33)
I RKNN: [10:37:07.387] RKNN Driver Information, version: 0.9.8
I RKNN: [10:37:07.397] RKNN Model Information, version: 6, toolkit version: 2.2.0(compiler version: 2.2.0 (c195366594@2024-09-14T12:24:14)), target: RKNPU v2, target platform: rk3588, framework name: ONNX, framework layout: NCHW, model inference type: dynamic_shape
Received ready signal: vision_ready
大概率rkllm进程崩掉了。你的开发板内存够大吗？
你可以试下更新后的代码，加了个错误打印
8G的内存，用htop看才用2.2G
8G那肯定不够，readme不是写了吗
- 内存占用(RK3588, 默认上下文长度): 视觉编码器 1.9GB + LLM 7.8GB = 9.7GB