[Feature] Huawei NPU Monitoring Support

[theone1900]

1Panel Version

v1.10.32-lts

Please describe your needs or suggestions for improvements

[root@localhost ~]# npu-smi info
+------------------------------------------------------------------------------------------------+
| npu-smi 24.1.1 Version: 24.1.1 |
+---------------------------+---------------+----------------------------------------------------+
| NPU Name | Health | Power(W) Temp(C) Hugepages-Usage(page)|
| Chip | Bus-Id | AICore(%) Memory-Usage(MB) HBM-Usage(MB) |
+===========================+===============+====================================================+
| 0 910B4 | OK | 88.2 30 0 / 0 |
| 0 | 0000:C1:00.0 | 0 0 / 0 26838/ 32768 |
+===========================+===============+====================================================+
| 1 910B4 | OK | 87.0 30 0 / 0 |
| 0 | 0000:C2:00.0 | 0 0 / 0 29356/ 32768 |
+===========================+===============+====================================================+
| 2 910B4 | OK | 85.1 30 0 / 0 |
| 0 | 0000:81:00.0 | 0 0 / 0 29356/ 32768 |
+===========================+===============+====================================================+
| 3 910B4 | OK | 86.9 33 0 / 0 |
| 0 | 0000:82:00.0 | 0 0 / 0 26899/ 32768 |
+===========================+===============+====================================================+
| 4 910B4 | OK | 86.4 34 0 / 0 |
| 0 | 0000:01:00.0 | 0 0 / 0 26900/ 32768 |
+===========================+===============+====================================================+
| 5 910B4 | OK | 83.9 34 0 / 0 |
| 0 | 0000:02:00.0 | 0 0 / 0 26900/ 32768 |
+===========================+===============+====================================================+
| 6 910B4 | OK | 90.8 34 0 / 0 |
| 0 | 0000:41:00.0 | 0 0 / 0 26900/ 32768 |
+===========================+===============+====================================================+
| 7 910B4 | OK | 84.5 34 0 / 0 |
| 0 | 0000:42:00.0 | 0 0 / 0 26900/ 32768 |
+===========================+===============+====================================================+
+---------------------------+---------------+----------------------------------------------------+
| NPU Chip | Process id | Process name | Process memory(MB) |
+===========================+===============+====================================================+
| 0 0 | 1406630 | mindie_llm_back | 21835 |
| 0 0 | 60575 | python | 2122 |
+===========================+===============+====================================================+
| 1 0 | 1584432 | python-text-emb | 2367 |
| 1 0 | 1406632 | mindie_llm_back | 24107 |
+===========================+===============+====================================================+
| 2 0 | 1598096 | python-text-emb | 2367 |
| 2 0 | 1406634 | mindie_llm_back | 24107 |
+===========================+===============+====================================================+
| 3 0 | 1406637 | mindie_llm_back | 24111 |
+===========================+===============+====================================================+
| 4 0 | 1406654 | mindie_llm_back | 24111 |
+===========================+===============+====================================================+
| 5 0 | 1406668 | mindie_llm_back | 24111 |
+===========================+===============+====================================================+
| 6 0 | 1406682 | mindie_llm_back | 24111 |
+===========================+===============+====================================================+
| 7 0 | 1406692 | mindie_llm_back | 24111 |
+===========================+===============+====================================================+

Please describe the solution you suggest

No response

Additional Information

No response

[wanghe-fit2cloud]

感谢反馈，能帮忙提供下设备让我们测试一下吗？

[YanLingLiu1]

您好，现在在GPU监控那里还是无法监控到NPU卡的相关信息，请问现在有办法进行监控吗？感谢