docker内 npu-smi info 报错
收藏回复举报
docker内 npu-smi info 报错
t('forum.solved') 已解决
发表于2023-05-09 11:58:10
0 查看
docker run -itd -u root \
--device=/dev/davinci0 \
--device=/dev/davinci_manager \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /var/log/npu:/var/log/npu \
-v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
-v /usr/slog:/usr/slog \
-v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/tools/:/usr/local/Ascend/driver/tools/ \
-v /usr/local/Ascend/add-ons/:/usr/local/Ascend/add-ons/ \
-v /data:/data \
ascendhub.huawei.com/public-ascendhub/infer-modelzoo:21.0.3 \
/bin/bash

容器拉起来的命令,

无法打印npu信息,报错如下

dcmi module initialize failed. ret is -8010

cke_6800.png

推理也失败

cke_10219.png

dev下有设备

cke_15600.png

/var/log/npu/slog/device-app-60/device-app-60_20230509035438983.log

cke_5664.png

/var/log/npu/slog/device-os/device-os_20230509035428981.log

[ERROR] DRV(60,main):2023-05-09-03:54:28.741.617 [hdc_core.c:389][hdc] [hdcPcieInit 389] HDC init fail, driver may not load.
[ERROR] DRV(60,main):2023-05-09-03:54:38.751.372 [hdc_core.c:374][hdc] [hdc_phandle_get 374] HDC init, open pcie device fail. error : No such file or directory

本帖最后由 匿名用户2023/05/09 14:59:33 编辑

我要发帖子